Created
January 31, 2020 15:21
-
-
Save ia35/2c044dc41644eb7884d210283e5c9e8f to your computer and use it in GitHub Desktop.
HyperparameterTuning.ipynb
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| { | |
| "nbformat": 4, | |
| "nbformat_minor": 0, | |
| "metadata": { | |
| "colab": { | |
| "name": "HyperparameterTuning.ipynb", | |
| "provenance": [], | |
| "collapsed_sections": [], | |
| "authorship_tag": "ABX9TyPCTF5YvkUl+X4dH5SIwQLq", | |
| "include_colab_link": true | |
| }, | |
| "kernelspec": { | |
| "name": "python3", | |
| "display_name": "Python 3" | |
| }, | |
| "accelerator": "GPU" | |
| }, | |
| "cells": [ | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "view-in-github", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "<a href=\"https://colab.research.google.com/gist/ia35/2c044dc41644eb7884d210283e5c9e8f/hyperparametertuning.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>" | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "NzZDucQPaohs", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "[](https://www.backprop.fr)" | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "rMvB1221jIhJ", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "L'article étudié ici est [Hyperparameter](https://blog.tensorflow.org/2020/01/hyperparameter-tuning-with-keras-tuner.html?linkId=81371017) tuning with Keras Tuner disponible sur le blog de TensorFlow" | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "_jJxt1pgvDZK", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "Il s'agit d'utiliser des outils qui permettent de trouver les meilleurs hyperparamètres du modèle. C'est un problème très important en machine learning. Il ne suffit pas d'avoir les bon modèles, les bonnes données, encore faut-il que les hyperparamètres soient bons !" | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "vzNg9ANrja-O", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "## <font color=\"teal\">Références</font>\n", | |
| "\n", | |
| "- [Hyperparameter](https://blog.tensorflow.org/2020/01/hyperparameter-tuning-with-keras-tuner.html?linkId=81371017) tuning with Keras Tuner\n", | |
| "- Keras Tuner CIFAR10 [example](https://github.com/keras-team/keras-tuner/blob/master/examples/cifar10.py) for the TensorFlow blog post\n", | |
| "- Keras Tuner [documentation](https://keras-team.github.io/keras-tuner/)" | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "KI2yu129au5D", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "[](https://www.backprop.fr)\n", | |
| "Le logo BackProp est présenté chaque fois qu'une modification importante est apportée au code ou à chaque fois qu'un commentaire doit être signalé. \n", | |
| "\n", | |
| "Le texte en anglais est soit le texte d'origine soit un extrait de site qui apporte des explications." | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "3KnRDE9Yayv4", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "[](https://www.backprop.fr)" | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "bVnq5kjIpqQy", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "J'ai parfois ajouté le texte de l'article directement dans le notebook afin qu'il soit self explicit" | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "AckVCL8ta2wi", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "## <font color=\"teal\">Introduction</font>" | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "sYVCsolBp1rQ", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "The success of a machine learning project is often crucially dependent on the choice of good hyperparameters. As machine learning continues to mature as a field, relying on trial and error to find good values for these parameters (also known as “grad student descent”) simply doesn’t scale. In fact, many of today’s state-of-the-art results, such as EfficientNet, were discovered via sophisticated hyperparameter optimization algorithms.\n", | |
| "\n", | |
| "Keras Tuner is an easy-to-use, distributable hyperparameter optimization framework that solves the pain points of performing a hyperparameter search. Keras Tuner makes it easy to define a search space and leverage included algorithms to find the best hyperparameter values. Keras Tuner comes with Bayesian Optimization, Hyperband, and Random Search algorithms built-in, and is also designed to be easy for researchers to extend in order to experiment with new search algorithms." | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "b0RoXKcep4v_", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "## <font color=\"teal\">Imports</font>" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "MVwEOWtFa7Z-", | |
| "colab_type": "code", | |
| "colab": { | |
| "base_uri": "https://localhost:8080/", | |
| "height": 71 | |
| }, | |
| "outputId": "f680a860-bc0a-4ed8-f4b5-99fe5bad826b" | |
| }, | |
| "source": [ | |
| "%tensorflow_version 2.x\n", | |
| "import tensorflow as tf\n", | |
| "print(tf.__version__)" | |
| ], | |
| "execution_count": 1, | |
| "outputs": [ | |
| { | |
| "output_type": "stream", | |
| "text": [ | |
| "TensorFlow 2.x selected.\n", | |
| "2.1.0\n" | |
| ], | |
| "name": "stdout" | |
| } | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "NFMnHIo6fvio", | |
| "colab_type": "code", | |
| "colab": {} | |
| }, | |
| "source": [ | |
| "import tensorflow_datasets as tfds" | |
| ], | |
| "execution_count": 0, | |
| "outputs": [] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "W5tsDvcb5JV0", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "L'option -U après le pip install \n", | |
| "\n", | |
| "Upgrade all specified packages to the newest available version. \n", | |
| "\n", | |
| "The handling of dependencies depends on the upgrade-strategy used." | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "Yu6rLBEtbJed", | |
| "colab_type": "code", | |
| "colab": { | |
| "base_uri": "https://localhost:8080/", | |
| "height": 286 | |
| }, | |
| "outputId": "0b927506-1824-4b0f-dbec-a3cecaa5093a" | |
| }, | |
| "source": [ | |
| "pip install -U keras-tuner" | |
| ], | |
| "execution_count": 3, | |
| "outputs": [ | |
| { | |
| "output_type": "stream", | |
| "text": [ | |
| "Requirement already up-to-date: keras-tuner in /usr/local/lib/python3.6/dist-packages (1.0.1)\n", | |
| "Requirement already satisfied, skipping upgrade: colorama in /usr/local/lib/python3.6/dist-packages (from keras-tuner) (0.4.3)\n", | |
| "Requirement already satisfied, skipping upgrade: future in /usr/local/lib/python3.6/dist-packages (from keras-tuner) (0.16.0)\n", | |
| "Requirement already satisfied, skipping upgrade: numpy in /tensorflow-2.1.0/python3.6 (from keras-tuner) (1.18.1)\n", | |
| "Requirement already satisfied, skipping upgrade: scikit-learn in /usr/local/lib/python3.6/dist-packages (from keras-tuner) (0.22.1)\n", | |
| "Requirement already satisfied, skipping upgrade: tqdm in /usr/local/lib/python3.6/dist-packages (from keras-tuner) (4.28.1)\n", | |
| "Requirement already satisfied, skipping upgrade: tabulate in /usr/local/lib/python3.6/dist-packages (from keras-tuner) (0.8.6)\n", | |
| "Requirement already satisfied, skipping upgrade: requests in /tensorflow-2.1.0/python3.6 (from keras-tuner) (2.22.0)\n", | |
| "Requirement already satisfied, skipping upgrade: terminaltables in /usr/local/lib/python3.6/dist-packages (from keras-tuner) (3.1.0)\n", | |
| "Requirement already satisfied, skipping upgrade: scipy in /tensorflow-2.1.0/python3.6 (from keras-tuner) (1.4.1)\n", | |
| "Requirement already satisfied, skipping upgrade: joblib>=0.11 in /usr/local/lib/python3.6/dist-packages (from scikit-learn->keras-tuner) (0.14.1)\n", | |
| "Requirement already satisfied, skipping upgrade: chardet<3.1.0,>=3.0.2 in /tensorflow-2.1.0/python3.6 (from requests->keras-tuner) (3.0.4)\n", | |
| "Requirement already satisfied, skipping upgrade: idna<2.9,>=2.5 in /tensorflow-2.1.0/python3.6 (from requests->keras-tuner) (2.8)\n", | |
| "Requirement already satisfied, skipping upgrade: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /tensorflow-2.1.0/python3.6 (from requests->keras-tuner) (1.25.7)\n", | |
| "Requirement already satisfied, skipping upgrade: certifi>=2017.4.17 in /tensorflow-2.1.0/python3.6 (from requests->keras-tuner) (2019.11.28)\n" | |
| ], | |
| "name": "stdout" | |
| } | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "MOZ6AAwhbnu0", | |
| "colab_type": "code", | |
| "colab": {} | |
| }, | |
| "source": [ | |
| "import kerastuner as kt" | |
| ], | |
| "execution_count": 0, | |
| "outputs": [] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "0bhYBikHqKM4", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "[](https://www.backprop.fr)" | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "_TBQjuFxqR0E", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "## <font color=\"teal\">Model</font>" | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "1iZYxsWiqGAF", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "Here’s a simple end-to-end example. \n", | |
| "\n", | |
| "First, we define a model-building function. \n", | |
| "\n", | |
| "It takes an **hp** argument from which you can sample hyperparameters, such as hp.Int('units', min_value=32, max_value=512, step=32) (an integer from a certain range)\n", | |
| "\n", | |
| "Notice how the hyperparameters can be defined inline with the model-building code. The example below creates a simple tunable model that we’ll train on CIFAR-10:" | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "sI6yCObEzEEc", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "Pour bien comprendre ce \"simple end-to-example\", on va le décortiquer pas à pas !" | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "WrdXggy5053_", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "La méthode est la suivante : \n", | |
| "- Tout d'abord on définit une fonction de création du modèle (model-building function) qui retourne un modèle compilé\n", | |
| "- Ensuite on instancie un tuner\n", | |
| "- Enfin on effectue la recherche des hyperparamètres\n", | |
| "\n", | |
| "On obtient ainsi le meilleur modèle calculé, qu'on peut utiliser." | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "gt0EjFmiCojd", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "[](https://www.backprop.fr)" | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "EMgxSE9q3NtF", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "## <font color=\"teal\">hp.Int</font>" | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "1ipSNjYH59zz", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "hp pour HyperParameters" | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "D3D5qILi7MEa", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "Integer range.\n", | |
| "\n", | |
| "Note that unlinke Python's range function, max_value is included in the possible values this parameter can take on.\n", | |
| "\n", | |
| "Arguments:\n", | |
| "\n", | |
| "- name: Str. Name of parameter. Must be unique.\n", | |
| "- min_value: Int. Lower limit of range (included).\n", | |
| "- max_value: Int. Upper limit of range (included).\n", | |
| "- step: Int. Step of range.\n", | |
| "- sampling: Optional. One of \"linear\", \"log\", \"reverse_log\". Acts as a hint for an initial prior probability distribution for how this value should be sampled, e.g. \"log\" will assign equal probabilities to each order of magnitude range.\n", | |
| "- default: Default value to return for the parameter. If unspecified, the default value will be min_value.\n", | |
| "- parent_name: (Optional) String. Specifies that this hyperparameter is conditional. The name of the this hyperparameter's parent. parent_values: (Optional) List. The values of the parent hyperparameter for which this hyperparameter should be considered active.\n", | |
| "\n", | |
| "\n", | |
| "Returns: \n", | |
| "\n", | |
| "The current value of this hyperparameter." | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "WvcfTy3lA0FA", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "[HyperParameters](https://keras-team.github.io/keras-tuner/documentation/hyperparameters/#int-method) class\n", | |
| "\n", | |
| "Container for both a hyperparameter space, and current values.\n", | |
| "\n", | |
| "Attributes:\n", | |
| "\n", | |
| "- space: A list of HyperParameter instances.\n", | |
| "- values: A dict mapping hyperparameter names to current values." | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "vHQUMLi_7mTY", | |
| "colab_type": "code", | |
| "colab": {} | |
| }, | |
| "source": [ | |
| "hp = kt.HyperParameters()" | |
| ], | |
| "execution_count": 0, | |
| "outputs": [] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "xXUNWP4s-i4z", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "On définit ici un hyperparamètre dont le nom est filters_1, donc la valeur minimale est 32, la maximale 256, le pas 32.\n", | |
| "\n", | |
| "Il y a donc 7 valeurs (256-32)/32\n", | |
| "\n", | |
| "La valeur initiale est 32 puisque par défaut elle est égale à min_value" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "3Zbnv91R8hYu", | |
| "colab_type": "code", | |
| "colab": {} | |
| }, | |
| "source": [ | |
| "filters = hp.Int('filters_' + str(1), 32, 256, step=32)" | |
| ], | |
| "execution_count": 0, | |
| "outputs": [] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "WHLrtj-N_Ksf", | |
| "colab_type": "code", | |
| "colab": { | |
| "base_uri": "https://localhost:8080/", | |
| "height": 54 | |
| }, | |
| "outputId": "88e43b34-e385-4359-ad8b-2acb0d0cd57e" | |
| }, | |
| "source": [ | |
| "filters" | |
| ], | |
| "execution_count": 7, | |
| "outputs": [ | |
| { | |
| "output_type": "execute_result", | |
| "data": { | |
| "text/plain": [ | |
| "32" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| }, | |
| "execution_count": 7 | |
| } | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "yDHWUcnoCYTE", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "values: A dict mapping hyperparameter names to current values." | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "7ZgCP9lQ8kI4", | |
| "colab_type": "code", | |
| "colab": { | |
| "base_uri": "https://localhost:8080/", | |
| "height": 54 | |
| }, | |
| "outputId": "5a61e728-c6fd-4fb9-e16b-c154ab564f5a" | |
| }, | |
| "source": [ | |
| "hp.values" | |
| ], | |
| "execution_count": 8, | |
| "outputs": [ | |
| { | |
| "output_type": "execute_result", | |
| "data": { | |
| "text/plain": [ | |
| "{'filters_1': 32}" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| }, | |
| "execution_count": 8 | |
| } | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "zxgi4-F7CkwH", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "space: A list of HyperParameter instances." | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "hTtk_k9V-F2o", | |
| "colab_type": "code", | |
| "colab": { | |
| "base_uri": "https://localhost:8080/", | |
| "height": 54 | |
| }, | |
| "outputId": "d7f0abc7-2345-4319-fcac-bbe4e808f775" | |
| }, | |
| "source": [ | |
| "hp.space" | |
| ], | |
| "execution_count": 9, | |
| "outputs": [ | |
| { | |
| "output_type": "execute_result", | |
| "data": { | |
| "text/plain": [ | |
| "[Int(name: \"filters_1\", min_value: 32, max_value: 256, step: 32, sampling: None, default: 32)]" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| }, | |
| "execution_count": 9 | |
| } | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "q7-X4KmuCrt3", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "[](https://www.backprop.fr)" | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "j4Xw0AQLCtoU", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "on crée un autre hyperparamètre" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "ASHmc5dc_0HX", | |
| "colab_type": "code", | |
| "colab": { | |
| "base_uri": "https://localhost:8080/", | |
| "height": 54 | |
| }, | |
| "outputId": "6d89f067-3496-4f04-e019-6a07fa9edc4f" | |
| }, | |
| "source": [ | |
| "ra = hp.Int('conv_blocks', 3, 5, default=3)\n", | |
| "ra" | |
| ], | |
| "execution_count": 10, | |
| "outputs": [ | |
| { | |
| "output_type": "execute_result", | |
| "data": { | |
| "text/plain": [ | |
| "3" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| }, | |
| "execution_count": 10 | |
| } | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "QObLyl0zC2yf", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "ce nouvel hyperparamètre est associé à l'espace hp" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "ldJF-Cja_6SB", | |
| "colab_type": "code", | |
| "colab": { | |
| "base_uri": "https://localhost:8080/", | |
| "height": 71 | |
| }, | |
| "outputId": "76578207-a308-4193-ad77-a6a5ffb0c8a4" | |
| }, | |
| "source": [ | |
| "hp.space" | |
| ], | |
| "execution_count": 11, | |
| "outputs": [ | |
| { | |
| "output_type": "execute_result", | |
| "data": { | |
| "text/plain": [ | |
| "[Int(name: \"filters_1\", min_value: 32, max_value: 256, step: 32, sampling: None, default: 32),\n", | |
| " Int(name: \"conv_blocks\", min_value: 3, max_value: 5, step: 1, sampling: None, default: 3)]" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| }, | |
| "execution_count": 11 | |
| } | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "p9n2H_FDDOHf", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "On voit qu'on a 2 hyperparamètres, tous deux initialisés avec les valeurs minimales" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "1rOyHS1rDKfi", | |
| "colab_type": "code", | |
| "colab": { | |
| "base_uri": "https://localhost:8080/", | |
| "height": 54 | |
| }, | |
| "outputId": "335a5f42-7332-4570-e2c8-c6cf2fb06872" | |
| }, | |
| "source": [ | |
| "hp.values" | |
| ], | |
| "execution_count": 12, | |
| "outputs": [ | |
| { | |
| "output_type": "execute_result", | |
| "data": { | |
| "text/plain": [ | |
| "{'conv_blocks': 3, 'filters_1': 32}" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| }, | |
| "execution_count": 12 | |
| } | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "eUBWllxvAOMF", | |
| "colab_type": "code", | |
| "colab": { | |
| "base_uri": "https://localhost:8080/", | |
| "height": 87 | |
| }, | |
| "outputId": "2e5d91f1-b356-46ce-9831-6fd7750561e9" | |
| }, | |
| "source": [ | |
| "for i in range(ra):\n", | |
| " print(i)" | |
| ], | |
| "execution_count": 13, | |
| "outputs": [ | |
| { | |
| "output_type": "stream", | |
| "text": [ | |
| "0\n", | |
| "1\n", | |
| "2\n" | |
| ], | |
| "name": "stdout" | |
| } | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "vKS0J0YHEOSA", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "Les lignes suivantes : \n", | |
| "\n", | |
| "for i in range(hp.Int('conv_blocks', 3, 5, default=3)):\n", | |
| "\n", | |
| "- filters = hp.Int('filters_' + str(i), 32, 256, step=32)\n", | |
| "\n", | |
| "créent 4 hyperparamètres : conv_blocks, filters_0, filters_1, filters_1, " | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "sHP9n9fWEmMV", | |
| "colab_type": "code", | |
| "colab": { | |
| "base_uri": "https://localhost:8080/", | |
| "height": 104 | |
| }, | |
| "outputId": "c4bf8d84-00d6-442f-f972-290567e09563" | |
| }, | |
| "source": [ | |
| "hp = kt.HyperParameters()\n", | |
| "for i in range(hp.Int('conv_blocks', 3, 5, default=3)):\n", | |
| " filters = hp.Int('filters_' + str(i), 32, 256, step=32)\n", | |
| "hp.space" | |
| ], | |
| "execution_count": 14, | |
| "outputs": [ | |
| { | |
| "output_type": "execute_result", | |
| "data": { | |
| "text/plain": [ | |
| "[Int(name: \"conv_blocks\", min_value: 3, max_value: 5, step: 1, sampling: None, default: 3),\n", | |
| " Int(name: \"filters_0\", min_value: 32, max_value: 256, step: 32, sampling: None, default: 32),\n", | |
| " Int(name: \"filters_1\", min_value: 32, max_value: 256, step: 32, sampling: None, default: 32),\n", | |
| " Int(name: \"filters_2\", min_value: 32, max_value: 256, step: 32, sampling: None, default: 32)]" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| }, | |
| "execution_count": 14 | |
| } | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "7JWPtirqKZtq", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "[](https://www.backprop.fr)" | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "ctzmYV3yzZBn", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "## <font color=\"teal\">hp.Choice</font>" | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "KyhtarLWJ7se", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "Choice of one value among a predefined set of possible values.\n", | |
| "\n", | |
| "Arguments:\n", | |
| "\n", | |
| "- name: Str. Name of parameter. Must be unique.\n", | |
| "- values: List of possible values. Values must be int, float, str, or bool. All values must be of the same type.\n", | |
| "- ordered: Whether the values passed should be considered to have an ordering. This defaults to True for float/int values. Must be False for any other values.\n", | |
| "- default: Default value to return for the parameter. If unspecified, the default value will be:\n", | |
| "-- None if None is one of the choices in values\n", | |
| "-- The first entry in values otherwise.\n", | |
| "\n", | |
| "parent_name: (Optional) String. Specifies that this hyperparameter is conditional. The name of the this hyperparameter's parent. \n", | |
| "\n", | |
| "parent_values: (Optional) List. The values of the parent hyperparameter for which this hyperparameter should be considered active.\n", | |
| "\n", | |
| "Returns:\n", | |
| "\n", | |
| "The current value of this hyperparameter." | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "tth-8-szLuhf", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "Que fait cette ligne de code : \n", | |
| "\n", | |
| "if hp.Choice('pooling_' + str(1), ['avg', 'max']) == 'max':\n", | |
| "\n" | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "AnfTNZ34L12D", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "hp.Choice crée d'abord un hyperparamètre. \n", | |
| "\n", | |
| "Le nom de cet hyperparamètre est pooling_1\n", | |
| "\n", | |
| "Les valeurs possibles pour cet hyperparamètre sont \"avg\" et \"max\"\n", | |
| "\n", | |
| "La valeur retournée, par défaut est \"avg\" car c'est la 1ère entrée" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "Ud66sxeNK7ob", | |
| "colab_type": "code", | |
| "colab": { | |
| "base_uri": "https://localhost:8080/", | |
| "height": 54 | |
| }, | |
| "outputId": "bf5fef6f-6494-484b-df5f-bd4e54457f5e" | |
| }, | |
| "source": [ | |
| "hp = kt.HyperParameters()\n", | |
| "if hp.Choice('pooling_' + str(1), ['avg', 'max']) == 'max':\n", | |
| " print (\"max\")\n", | |
| "else:\n", | |
| " print (\"avg\")" | |
| ], | |
| "execution_count": 15, | |
| "outputs": [ | |
| { | |
| "output_type": "stream", | |
| "text": [ | |
| "avg\n" | |
| ], | |
| "name": "stdout" | |
| } | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "ihXk8wt6LRj7", | |
| "colab_type": "code", | |
| "colab": { | |
| "base_uri": "https://localhost:8080/", | |
| "height": 54 | |
| }, | |
| "outputId": "bf55af6c-217d-488d-b326-c9096a8163a8" | |
| }, | |
| "source": [ | |
| "hp.space" | |
| ], | |
| "execution_count": 16, | |
| "outputs": [ | |
| { | |
| "output_type": "execute_result", | |
| "data": { | |
| "text/plain": [ | |
| "[Choice(name: \"pooling_1\", values: ['avg', 'max'], ordered: False, default: avg)]" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| }, | |
| "execution_count": 16 | |
| } | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "kv8R1_TrS0J3", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "## <font color=\"teal\">build_model</font>" | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "2VEL4ZNvpvk9", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "Cette façon de créer des couches n'est pas classique. \n", | |
| "On fait rarement des boucles pour créer un modèle. \n", | |
| "\n", | |
| "On crée plutôt des blocs qu'on répète.\n", | |
| "\n", | |
| "Ceci étant dit, l'architecture est la suivante (avec les paramètres par défaut)\n", | |
| "\n", | |
| "- (InputLayer) [(None, 32, 32, 3)] \n", | |
| "\n", | |
| "\n", | |
| "---\n", | |
| "\n", | |
| "\n", | |
| "Boucle (A) de création (0, 1, 2)\n", | |
| "\n", | |
| "---\n", | |
| "A0\n", | |
| "\n", | |
| "Boucle (B) de création (0,1)\n", | |
| "\n", | |
| "A0 - B0\n", | |
| "\n", | |
| "- - (Conv2D) (None, 32, 32, 32)\n", | |
| "- - (batch_normalization) (None, 32, 32, 32)\n", | |
| "- - (ReLU) (None, 32, 32, 32)\n", | |
| "\n", | |
| "A0 - B1\n", | |
| "\n", | |
| "- - (Conv2D) (None, 32, 32, 32)\n", | |
| "- - (batch_normalization) (None, 32, 32, 32)\n", | |
| "- - (ReLU) (None, 32, 32, 32) \n", | |
| "\n", | |
| "A0 \n", | |
| "\n", | |
| "- (Average Pooling (None, 16, 16, 32) \n", | |
| "---\n", | |
| "\n", | |
| "\n", | |
| "A1\n", | |
| "\n", | |
| "Boucle (B) de création (0,1)\n", | |
| "\n", | |
| "A1 - B0\n", | |
| "\n", | |
| "- - (Conv2D) (None, 32, 32, 32)\n", | |
| "- - (batch_normalization) (None, 32, 32, 32)\n", | |
| "- - (ReLU) (None, 32, 32, 32)\n", | |
| "\n", | |
| "A1 - B1\n", | |
| "\n", | |
| "- - (Conv2D) (None, 32, 32, 32)\n", | |
| "- - (batch_normalization) (None, 32, 32, 32)\n", | |
| "- - (ReLU) (None, 32, 32, 32) \n", | |
| "\n", | |
| "A1 \n", | |
| "\n", | |
| "- (Average Pooling (None, 16, 16, 32) \n", | |
| "---\n", | |
| "\n", | |
| "\n", | |
| "A2\n", | |
| "\n", | |
| "Boucle (B) de création (0,1)\n", | |
| "\n", | |
| "A2 - B0\n", | |
| "\n", | |
| "- - (Conv2D) (None, 32, 32, 32)\n", | |
| "- - (batch_normalization) (None, 32, 32, 32)\n", | |
| "- - (ReLU) (None, 32, 32, 32)\n", | |
| "\n", | |
| "A2 - B1\n", | |
| "\n", | |
| "\n", | |
| "- - (Conv2D) (None, 32, 32, 32)\n", | |
| "- - (batch_normalization) (None, 32, 32, 32)\n", | |
| "- - (ReLU) (None, 32, 32, 32) \n", | |
| "\n", | |
| "A2 \n", | |
| "\n", | |
| "- (Average Pooling (None, 16, 16, 32) \n", | |
| "---\n", | |
| "\n", | |
| "- global_average_pooling2d (None, 32)\n", | |
| "- (Dense) (None, 50) \n", | |
| "- (Dropout) (None, 50)\n", | |
| "- (Dense) (None, 10)\n" | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "EwJt5oc6BGly", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "Il faut bien comprendre qu'on n'a pas toujours la même architecture puisque conv_blocks est dans l'intervalle 3..5" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "eRIAA6PXaiY9", | |
| "colab_type": "code", | |
| "colab": {} | |
| }, | |
| "source": [ | |
| "def build_model(hp):\n", | |
| "\n", | |
| " inputs = tf.keras.Input(shape=(32, 32, 3))\n", | |
| " x = inputs\n", | |
| "\n", | |
| " for i in range(hp.Int('conv_blocks', 3, 5, default=3)):\n", | |
| " filters = hp.Int('filters_' + str(i), 32, 256, step=32)\n", | |
| " for _ in range(2):\n", | |
| " x = tf.keras.layers.Convolution2D(\n", | |
| " filters, kernel_size=(3, 3), padding='same')(x)\n", | |
| " x = tf.keras.layers.BatchNormalization()(x)\n", | |
| " x = tf.keras.layers.ReLU()(x)\n", | |
| " if hp.Choice('pooling_' + str(i), ['avg', 'max']) == 'max':\n", | |
| " x = tf.keras.layers.MaxPool2D()(x)\n", | |
| " else:\n", | |
| " x = tf.keras.layers.AvgPool2D()(x)\n", | |
| "\n", | |
| " x = tf.keras.layers.GlobalAvgPool2D()(x)\n", | |
| " x = tf.keras.layers.Dense(\n", | |
| " hp.Int('hidden_size', 30, 100, step=10, default=50),\n", | |
| " activation='relu')(x)\n", | |
| "\n", | |
| " x = tf.keras.layers.Dropout(\n", | |
| " hp.Float('dropout', 0, 0.5, step=0.1, default=0.5))(x)\n", | |
| " outputs = tf.keras.layers.Dense(10, activation='softmax')(x)\n", | |
| "\n", | |
| " model = tf.keras.Model(inputs, outputs)\n", | |
| " \n", | |
| " model.compile(\n", | |
| " optimizer=tf.keras.optimizers.Adam(\n", | |
| " hp.Float('learning_rate', 1e-4, 1e-2, sampling='log')),\n", | |
| " loss='sparse_categorical_crossentropy', \n", | |
| " metrics=['accuracy'])\n", | |
| " return model" | |
| ], | |
| "execution_count": 0, | |
| "outputs": [] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "5kELRRkIWfGe", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "[](https://www.backprop.fr)" | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "RYy8JqEyWPCF", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "Voyons ce que donne ce modèle : " | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "IX3oE-ZHVyNz", | |
| "colab_type": "code", | |
| "colab": {} | |
| }, | |
| "source": [ | |
| "hp = kt.HyperParameters()\n", | |
| "myModel=build_model(hp)" | |
| ], | |
| "execution_count": 0, | |
| "outputs": [] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "vlieh20fYI8Z", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "Les hyperparamètres sont : \n", | |
| "\n", | |
| "- \"conv_blocks\", min_value: 3, max_value: 5, step: 1, sampling: None, default: 3),\n", | |
| "- \"filters_0\", min_value: 32, max_value: 256, step: 32, sampling: None, default: 32),\n", | |
| "- \"pooling_0\", values: ['avg', 'max'], ordered: False, default: avg),\n", | |
| "- \"filters_1\", min_value: 32, max_value: 256, step: 32, sampling: None, default: 32),\n", | |
| "- \"pooling_1\", values: ['avg', 'max'], ordered: False, default: avg),\n", | |
| "- \"filters_2\", min_value: 32, max_value: 256, step: 32, sampling: None, default: 32),\n", | |
| "- \"pooling_2\", values: ['avg', 'max'], ordered: False, default: avg),\n", | |
| "- \"hidden_size\", min_value: 30, max_value: 100, step: 10, sampling: None, default: 50),\n", | |
| "- \"dropout\", min_value: 0.0, max_value: 0.5, step: 0.1, sampling: None, default: 0.5),\n", | |
| "- \"learning_rate\", min_value: 0.0001, max_value: 0.01, step: None, sampling: log, default: 0.0001)]" | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "88I66acYeL6N", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "- conv_blocks est créé ligne 6\n", | |
| "- filters_0, filters_1 et filters_2 sont créés ligne 7 (boucle)\n", | |
| "- pooling_0, pooling_1 et pooling_2 sont créés ligne 13 (boucle)\n", | |
| "- hidden_size est créé ligne 20\n", | |
| "- dropout est créé ligne 24\n", | |
| "- learning_rate est créé ligne 31 dans model.compile\n" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "29BazklkW5vi", | |
| "colab_type": "code", | |
| "colab": { | |
| "base_uri": "https://localhost:8080/", | |
| "height": 203 | |
| }, | |
| "outputId": "9df72118-2a7e-47dc-b104-69c8ea83c5b0" | |
| }, | |
| "source": [ | |
| "hp.space" | |
| ], | |
| "execution_count": 19, | |
| "outputs": [ | |
| { | |
| "output_type": "execute_result", | |
| "data": { | |
| "text/plain": [ | |
| "[Int(name: \"conv_blocks\", min_value: 3, max_value: 5, step: 1, sampling: None, default: 3),\n", | |
| " Int(name: \"filters_0\", min_value: 32, max_value: 256, step: 32, sampling: None, default: 32),\n", | |
| " Choice(name: \"pooling_0\", values: ['avg', 'max'], ordered: False, default: avg),\n", | |
| " Int(name: \"filters_1\", min_value: 32, max_value: 256, step: 32, sampling: None, default: 32),\n", | |
| " Choice(name: \"pooling_1\", values: ['avg', 'max'], ordered: False, default: avg),\n", | |
| " Int(name: \"filters_2\", min_value: 32, max_value: 256, step: 32, sampling: None, default: 32),\n", | |
| " Choice(name: \"pooling_2\", values: ['avg', 'max'], ordered: False, default: avg),\n", | |
| " Int(name: \"hidden_size\", min_value: 30, max_value: 100, step: 10, sampling: None, default: 50),\n", | |
| " Float(name: \"dropout\", min_value: 0.0, max_value: 0.5, step: 0.1, sampling: None, default: 0.5),\n", | |
| " Float(name: \"learning_rate\", min_value: 0.0001, max_value: 0.01, step: None, sampling: log, default: 0.0001)]" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| }, | |
| "execution_count": 19 | |
| } | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "Sm_0H8tvWXUK", | |
| "colab_type": "code", | |
| "colab": { | |
| "base_uri": "https://localhost:8080/", | |
| "height": 1000 | |
| }, | |
| "outputId": "acf71ae4-c858-44e3-c5b8-7070d679d65a" | |
| }, | |
| "source": [ | |
| "myModel.summary()" | |
| ], | |
| "execution_count": 20, | |
| "outputs": [ | |
| { | |
| "output_type": "stream", | |
| "text": [ | |
| "Model: \"model\"\n", | |
| "_________________________________________________________________\n", | |
| "Layer (type) Output Shape Param # \n", | |
| "=================================================================\n", | |
| "input_1 (InputLayer) [(None, 32, 32, 3)] 0 \n", | |
| "_________________________________________________________________\n", | |
| "conv2d (Conv2D) (None, 32, 32, 32) 896 \n", | |
| "_________________________________________________________________\n", | |
| "batch_normalization (BatchNo (None, 32, 32, 32) 128 \n", | |
| "_________________________________________________________________\n", | |
| "re_lu (ReLU) (None, 32, 32, 32) 0 \n", | |
| "_________________________________________________________________\n", | |
| "conv2d_1 (Conv2D) (None, 32, 32, 32) 9248 \n", | |
| "_________________________________________________________________\n", | |
| "batch_normalization_1 (Batch (None, 32, 32, 32) 128 \n", | |
| "_________________________________________________________________\n", | |
| "re_lu_1 (ReLU) (None, 32, 32, 32) 0 \n", | |
| "_________________________________________________________________\n", | |
| "average_pooling2d (AveragePo (None, 16, 16, 32) 0 \n", | |
| "_________________________________________________________________\n", | |
| "conv2d_2 (Conv2D) (None, 16, 16, 32) 9248 \n", | |
| "_________________________________________________________________\n", | |
| "batch_normalization_2 (Batch (None, 16, 16, 32) 128 \n", | |
| "_________________________________________________________________\n", | |
| "re_lu_2 (ReLU) (None, 16, 16, 32) 0 \n", | |
| "_________________________________________________________________\n", | |
| "conv2d_3 (Conv2D) (None, 16, 16, 32) 9248 \n", | |
| "_________________________________________________________________\n", | |
| "batch_normalization_3 (Batch (None, 16, 16, 32) 128 \n", | |
| "_________________________________________________________________\n", | |
| "re_lu_3 (ReLU) (None, 16, 16, 32) 0 \n", | |
| "_________________________________________________________________\n", | |
| "average_pooling2d_1 (Average (None, 8, 8, 32) 0 \n", | |
| "_________________________________________________________________\n", | |
| "conv2d_4 (Conv2D) (None, 8, 8, 32) 9248 \n", | |
| "_________________________________________________________________\n", | |
| "batch_normalization_4 (Batch (None, 8, 8, 32) 128 \n", | |
| "_________________________________________________________________\n", | |
| "re_lu_4 (ReLU) (None, 8, 8, 32) 0 \n", | |
| "_________________________________________________________________\n", | |
| "conv2d_5 (Conv2D) (None, 8, 8, 32) 9248 \n", | |
| "_________________________________________________________________\n", | |
| "batch_normalization_5 (Batch (None, 8, 8, 32) 128 \n", | |
| "_________________________________________________________________\n", | |
| "re_lu_5 (ReLU) (None, 8, 8, 32) 0 \n", | |
| "_________________________________________________________________\n", | |
| "average_pooling2d_2 (Average (None, 4, 4, 32) 0 \n", | |
| "_________________________________________________________________\n", | |
| "global_average_pooling2d (Gl (None, 32) 0 \n", | |
| "_________________________________________________________________\n", | |
| "dense (Dense) (None, 50) 1650 \n", | |
| "_________________________________________________________________\n", | |
| "dropout (Dropout) (None, 50) 0 \n", | |
| "_________________________________________________________________\n", | |
| "dense_1 (Dense) (None, 10) 510 \n", | |
| "=================================================================\n", | |
| "Total params: 50,064\n", | |
| "Trainable params: 49,680\n", | |
| "Non-trainable params: 384\n", | |
| "_________________________________________________________________\n" | |
| ], | |
| "name": "stdout" | |
| } | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "KXJcVAR4bAtn", | |
| "colab_type": "code", | |
| "colab": {} | |
| }, | |
| "source": [ | |
| "tuner = kt.Hyperband(\n", | |
| " build_model,\n", | |
| " objective='val_accuracy',\n", | |
| " max_epochs=30,\n", | |
| " hyperband_iterations=2)" | |
| ], | |
| "execution_count": 0, | |
| "outputs": [] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "xk9eNnzPSiZN", | |
| "colab_type": "code", | |
| "colab": { | |
| "base_uri": "https://localhost:8080/", | |
| "height": 1000 | |
| }, | |
| "outputId": "887a1838-35ad-4577-e4db-85601ac6d07e" | |
| }, | |
| "source": [ | |
| "tuner.search_space_summary()" | |
| ], | |
| "execution_count": 22, | |
| "outputs": [ | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#4527A0\"><h1 style=\"font-size:18px\">Search space summary</h1></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Default search space size: 10</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">conv_blocks (Int)</h2></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-default: 3</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-max_value: 5</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-min_value: 3</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-sampling: None</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-step: 1</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">filters_0 (Int)</h2></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-default: None</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-max_value: 256</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-min_value: 32</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-sampling: None</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-step: 32</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">pooling_0 (Choice)</h2></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-default: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-ordered: False</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-values: ['avg', 'max']</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">filters_1 (Int)</h2></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-default: None</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-max_value: 256</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-min_value: 32</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-sampling: None</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-step: 32</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">pooling_1 (Choice)</h2></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-default: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-ordered: False</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-values: ['avg', 'max']</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">filters_2 (Int)</h2></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-default: None</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-max_value: 256</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-min_value: 32</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-sampling: None</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-step: 32</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">pooling_2 (Choice)</h2></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-default: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-ordered: False</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-values: ['avg', 'max']</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">hidden_size (Int)</h2></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-default: 50</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-max_value: 100</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-min_value: 30</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-sampling: None</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-step: 10</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">dropout (Float)</h2></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-default: 0.5</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-max_value: 0.5</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-min_value: 0.0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-sampling: None</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-step: 0.1</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">learning_rate (Float)</h2></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-default: 0.0001</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-max_value: 0.01</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-min_value: 0.0001</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-sampling: log</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-step: None</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| } | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "hZ6fLuoYbDhX", | |
| "colab_type": "code", | |
| "colab": {} | |
| }, | |
| "source": [ | |
| "data = tfds.load('cifar10')\n", | |
| "train_ds, test_ds = data['train'], data['test']" | |
| ], | |
| "execution_count": 0, | |
| "outputs": [] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "KzJRNfVCf2BV", | |
| "colab_type": "code", | |
| "colab": {} | |
| }, | |
| "source": [ | |
| "def standardize_record(record):\n", | |
| " return tf.cast(record['image'], tf.float32) / 255., record['label']" | |
| ], | |
| "execution_count": 0, | |
| "outputs": [] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "XwcCqst1gSqV", | |
| "colab_type": "code", | |
| "colab": {} | |
| }, | |
| "source": [ | |
| "train_ds = train_ds.map(standardize_record).cache().batch(64).shuffle(10000)\n", | |
| "test_ds = test_ds.map(standardize_record).cache().batch(64)" | |
| ], | |
| "execution_count": 0, | |
| "outputs": [] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "xRxS_MuYrWJv", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "Next, instantiate a tuner. You should specify the model-building function, and the name of the objective to optimize (whether to minimize or maximize is automatically inferred for built-in metrics -- for custom metrics you can specify this via the kerastuner.Objective class). In this example, Keras tuner will use the Hyperband algorithm for the hyperparameter search:" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "yWGfZlmKf40N", | |
| "colab_type": "code", | |
| "colab": { | |
| "base_uri": "https://localhost:8080/", | |
| "height": 1000 | |
| }, | |
| "outputId": "71fb1035-67ea-4ccf-e95a-9228d41bd1d3" | |
| }, | |
| "source": [ | |
| "tuner.search(train_ds,\n", | |
| " validation_data=test_ds,\n", | |
| " epochs=3,\n", | |
| " callbacks=[tf.keras.callbacks.EarlyStopping(patience=1)])" | |
| ], | |
| "execution_count": 29, | |
| "outputs": [ | |
| { | |
| "output_type": "stream", | |
| "text": [ | |
| "Epoch 1/2\n", | |
| "782/782 [==============================] - 40s 51ms/step - loss: 1.3070 - accuracy: 0.5304 - val_loss: 1.2190 - val_accuracy: 0.5566\n", | |
| "Epoch 2/2\n", | |
| "782/782 [==============================] - 23s 30ms/step - loss: 0.8673 - accuracy: 0.6968 - val_loss: 0.8452 - val_accuracy: 0.6974\n" | |
| ], | |
| "name": "stdout" | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#4527A0\"><h1 style=\"font-size:18px\">Trial complete</h1></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#4527A0\"><h1 style=\"font-size:18px\">Trial summary</h1></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Trial ID: f71bedff001aea21954347c8fd008d09</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Score: 0.6973999738693237</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Best step: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">Hyperparameters:</h2></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-conv_blocks: 3</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-dropout: 0.30000000000000004</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-filters_0: 128</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-filters_1: 160</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-filters_2: 256</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-hidden_size: 100</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-learning_rate: 0.0005452907696240787</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-pooling_0: max</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-pooling_1: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-pooling_2: max</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-tuner/bracket: 3</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-tuner/epochs: 2</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-tuner/initial_epoch: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-tuner/round: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "stream", | |
| "text": [ | |
| "Epoch 1/2\n", | |
| "782/782 [==============================] - 34s 44ms/step - loss: 1.5504 - accuracy: 0.4340 - val_loss: 1.4544 - val_accuracy: 0.5016\n", | |
| "Epoch 2/2\n", | |
| "782/782 [==============================] - 31s 40ms/step - loss: 1.0339 - accuracy: 0.6441 - val_loss: 1.3428 - val_accuracy: 0.5475\n" | |
| ], | |
| "name": "stdout" | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#4527A0\"><h1 style=\"font-size:18px\">Trial complete</h1></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#4527A0\"><h1 style=\"font-size:18px\">Trial summary</h1></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Trial ID: 929d9ebe279d2feb136b5f5c4e436863</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Score: 0.5475000143051147</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Best step: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">Hyperparameters:</h2></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-conv_blocks: 4</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-dropout: 0.4</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-filters_0: 192</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-filters_1: 128</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-filters_2: 160</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-filters_3: 32</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-hidden_size: 40</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-learning_rate: 0.0010848539808730223</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-pooling_0: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-pooling_1: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-pooling_2: max</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-pooling_3: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-tuner/bracket: 3</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-tuner/epochs: 2</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-tuner/initial_epoch: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-tuner/round: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "stream", | |
| "text": [ | |
| "Epoch 1/2\n", | |
| "782/782 [==============================] - 20s 26ms/step - loss: 1.6190 - accuracy: 0.3943 - val_loss: 1.9074 - val_accuracy: 0.3842\n", | |
| "Epoch 2/2\n", | |
| "782/782 [==============================] - 16s 20ms/step - loss: 1.1158 - accuracy: 0.6072 - val_loss: 1.5324 - val_accuracy: 0.5174\n" | |
| ], | |
| "name": "stdout" | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#4527A0\"><h1 style=\"font-size:18px\">Trial complete</h1></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#4527A0\"><h1 style=\"font-size:18px\">Trial summary</h1></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Trial ID: 8495a0d853d8d3d38707a2cbed7c2805</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Score: 0.5174000263214111</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Best step: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">Hyperparameters:</h2></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-conv_blocks: 4</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-dropout: 0.1</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-filters_0: 64</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-filters_1: 128</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-filters_2: 192</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-filters_3: 192</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-hidden_size: 70</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-learning_rate: 0.009204492527981334</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-pooling_0: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-pooling_1: max</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-pooling_2: max</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-pooling_3: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-tuner/bracket: 3</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-tuner/epochs: 2</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-tuner/initial_epoch: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-tuner/round: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "stream", | |
| "text": [ | |
| "Epoch 1/2\n", | |
| "782/782 [==============================] - 25s 33ms/step - loss: 1.2284 - accuracy: 0.5615 - val_loss: 1.1633 - val_accuracy: 0.5953\n", | |
| "Epoch 2/2\n", | |
| "782/782 [==============================] - 22s 28ms/step - loss: 0.7434 - accuracy: 0.7403 - val_loss: 1.0062 - val_accuracy: 0.6475\n" | |
| ], | |
| "name": "stdout" | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#4527A0\"><h1 style=\"font-size:18px\">Trial complete</h1></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#4527A0\"><h1 style=\"font-size:18px\">Trial summary</h1></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Trial ID: 6ead717d86b79ff4516ae149a92fae3c</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Score: 0.6474999785423279</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Best step: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">Hyperparameters:</h2></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-conv_blocks: 4</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-dropout: 0.0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-filters_0: 96</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-filters_1: 192</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-filters_2: 192</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-filters_3: 96</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-hidden_size: 60</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-learning_rate: 0.00017635477591562107</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-pooling_0: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-pooling_1: max</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-pooling_2: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-pooling_3: max</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-tuner/bracket: 3</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-tuner/epochs: 2</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-tuner/initial_epoch: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-tuner/round: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "stream", | |
| "text": [ | |
| "Epoch 1/2\n", | |
| "782/782 [==============================] - 20s 25ms/step - loss: 1.1740 - accuracy: 0.5791 - val_loss: 1.0384 - val_accuracy: 0.6334\n", | |
| "Epoch 2/2\n", | |
| "782/782 [==============================] - 15s 20ms/step - loss: 0.7222 - accuracy: 0.7471 - val_loss: 1.0836 - val_accuracy: 0.6399\n" | |
| ], | |
| "name": "stdout" | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#4527A0\"><h1 style=\"font-size:18px\">Trial complete</h1></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#4527A0\"><h1 style=\"font-size:18px\">Trial summary</h1></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Trial ID: b42efd26af096b2792eab70be5367f0c</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Score: 0.6399000287055969</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Best step: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">Hyperparameters:</h2></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-conv_blocks: 4</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-dropout: 0.0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-filters_0: 32</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-filters_1: 192</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-filters_2: 160</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-filters_3: 224</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-hidden_size: 60</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-learning_rate: 0.0002354738695108064</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-pooling_0: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-pooling_1: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-pooling_2: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-pooling_3: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-tuner/bracket: 3</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-tuner/epochs: 2</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-tuner/initial_epoch: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-tuner/round: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "stream", | |
| "text": [ | |
| "Epoch 1/2\n", | |
| "782/782 [==============================] - 32s 41ms/step - loss: 1.6382 - accuracy: 0.4290 - val_loss: 1.2917 - val_accuracy: 0.5636\n", | |
| "Epoch 2/2\n", | |
| "782/782 [==============================] - 29s 37ms/step - loss: 1.0638 - accuracy: 0.6482 - val_loss: 1.1828 - val_accuracy: 0.6005\n" | |
| ], | |
| "name": "stdout" | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#4527A0\"><h1 style=\"font-size:18px\">Trial complete</h1></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#4527A0\"><h1 style=\"font-size:18px\">Trial summary</h1></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Trial ID: b481d7ae3d880ccda1208d8e1892d677</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Score: 0.6004999876022339</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Best step: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">Hyperparameters:</h2></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-conv_blocks: 5</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-dropout: 0.4</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-filters_0: 192</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-filters_1: 64</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-filters_2: 64</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-filters_3: 256</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-filters_4: 32</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-hidden_size: 60</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-learning_rate: 0.00013392077338679055</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-pooling_0: max</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-pooling_1: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-pooling_2: max</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-pooling_3: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-pooling_4: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-tuner/bracket: 3</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-tuner/epochs: 2</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-tuner/initial_epoch: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-tuner/round: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "stream", | |
| "text": [ | |
| "Epoch 1/2\n", | |
| "782/782 [==============================] - 19s 24ms/step - loss: 1.6538 - accuracy: 0.3717 - val_loss: 1.9047 - val_accuracy: 0.3833\n", | |
| "Epoch 2/2\n", | |
| "782/782 [==============================] - 15s 19ms/step - loss: 1.2310 - accuracy: 0.5662 - val_loss: 1.1329 - val_accuracy: 0.6093\n" | |
| ], | |
| "name": "stdout" | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#4527A0\"><h1 style=\"font-size:18px\">Trial complete</h1></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#4527A0\"><h1 style=\"font-size:18px\">Trial summary</h1></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Trial ID: fd92c7a704d4702e345b4d6120f9ceb1</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Score: 0.6093000173568726</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Best step: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">Hyperparameters:</h2></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-conv_blocks: 4</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-dropout: 0.30000000000000004</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-filters_0: 32</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-filters_1: 160</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-filters_2: 224</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-filters_3: 128</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-filters_4: 192</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-hidden_size: 50</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-learning_rate: 0.005957508426809308</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-pooling_0: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-pooling_1: max</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-pooling_2: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-pooling_3: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-pooling_4: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-tuner/bracket: 3</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-tuner/epochs: 2</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-tuner/initial_epoch: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-tuner/round: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "stream", | |
| "text": [ | |
| "Epoch 1/2\n", | |
| "782/782 [==============================] - 25s 32ms/step - loss: 1.3146 - accuracy: 0.5291 - val_loss: 0.9642 - val_accuracy: 0.6589\n", | |
| "Epoch 2/2\n", | |
| "782/782 [==============================] - 22s 28ms/step - loss: 0.7977 - accuracy: 0.7236 - val_loss: 0.7403 - val_accuracy: 0.7381\n" | |
| ], | |
| "name": "stdout" | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#4527A0\"><h1 style=\"font-size:18px\">Trial complete</h1></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#4527A0\"><h1 style=\"font-size:18px\">Trial summary</h1></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Trial ID: 0d1b4022b147f4b2e38d29fabc4ba7ff</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Score: 0.738099992275238</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Best step: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">Hyperparameters:</h2></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-conv_blocks: 4</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-dropout: 0.1</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-filters_0: 96</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-filters_1: 192</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-filters_2: 160</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-filters_3: 192</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-filters_4: 192</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-hidden_size: 30</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-learning_rate: 0.0003143963712950679</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-pooling_0: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-pooling_1: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-pooling_2: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-pooling_3: max</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-pooling_4: max</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-tuner/bracket: 3</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-tuner/epochs: 2</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-tuner/initial_epoch: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-tuner/round: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "stream", | |
| "text": [ | |
| "Epoch 1/2\n", | |
| "782/782 [==============================] - 16s 21ms/step - loss: 1.4603 - accuracy: 0.4878 - val_loss: 1.2612 - val_accuracy: 0.5516\n", | |
| "Epoch 2/2\n", | |
| "782/782 [==============================] - 12s 15ms/step - loss: 1.0196 - accuracy: 0.6566 - val_loss: 1.0802 - val_accuracy: 0.6337\n" | |
| ], | |
| "name": "stdout" | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#4527A0\"><h1 style=\"font-size:18px\">Trial complete</h1></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#4527A0\"><h1 style=\"font-size:18px\">Trial summary</h1></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Trial ID: 0e7ccb572dbedf1e7f9ef6c08cde4d67</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Score: 0.6337000131607056</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Best step: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">Hyperparameters:</h2></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-conv_blocks: 4</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-dropout: 0.30000000000000004</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-filters_0: 32</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-filters_1: 64</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-filters_2: 256</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-filters_3: 224</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-filters_4: 96</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-hidden_size: 30</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-learning_rate: 0.0001855349762763219</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-pooling_0: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-pooling_1: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-pooling_2: max</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-pooling_3: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-pooling_4: max</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-tuner/bracket: 3</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-tuner/epochs: 2</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-tuner/initial_epoch: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-tuner/round: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "stream", | |
| "text": [ | |
| "Epoch 1/2\n", | |
| "782/782 [==============================] - 22s 28ms/step - loss: 1.5077 - accuracy: 0.4636 - val_loss: 1.2764 - val_accuracy: 0.5431\n", | |
| "Epoch 2/2\n", | |
| "782/782 [==============================] - 18s 23ms/step - loss: 0.9872 - accuracy: 0.6630 - val_loss: 0.9114 - val_accuracy: 0.6822\n" | |
| ], | |
| "name": "stdout" | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#4527A0\"><h1 style=\"font-size:18px\">Trial complete</h1></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#4527A0\"><h1 style=\"font-size:18px\">Trial summary</h1></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Trial ID: 682e8075b5f3afdf692a83b35ad68868</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Score: 0.682200014591217</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Best step: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">Hyperparameters:</h2></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-conv_blocks: 5</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-dropout: 0.30000000000000004</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-filters_0: 64</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-filters_1: 160</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-filters_2: 160</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-filters_3: 192</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-filters_4: 64</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-hidden_size: 80</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-learning_rate: 0.0001304185747067234</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-pooling_0: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-pooling_1: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-pooling_2: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-pooling_3: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-pooling_4: max</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-tuner/bracket: 3</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-tuner/epochs: 2</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-tuner/initial_epoch: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-tuner/round: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "stream", | |
| "text": [ | |
| "Epoch 1/2\n", | |
| "782/782 [==============================] - 29s 37ms/step - loss: 1.4388 - accuracy: 0.4879 - val_loss: 1.1877 - val_accuracy: 0.5784\n", | |
| "Epoch 2/2\n", | |
| "782/782 [==============================] - 26s 33ms/step - loss: 0.9882 - accuracy: 0.6599 - val_loss: 1.0256 - val_accuracy: 0.6433\n" | |
| ], | |
| "name": "stdout" | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#4527A0\"><h1 style=\"font-size:18px\">Trial complete</h1></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#4527A0\"><h1 style=\"font-size:18px\">Trial summary</h1></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Trial ID: c51ec061893a5e1f3fae3e3f763f786b</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Score: 0.6432999968528748</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Best step: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">Hyperparameters:</h2></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-conv_blocks: 4</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-dropout: 0.2</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-filters_0: 160</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-filters_1: 64</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-filters_2: 96</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-filters_3: 224</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-filters_4: 128</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-hidden_size: 40</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-learning_rate: 0.00012848373778229555</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-pooling_0: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-pooling_1: max</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-pooling_2: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-pooling_3: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-pooling_4: max</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-tuner/bracket: 3</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-tuner/epochs: 2</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-tuner/initial_epoch: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-tuner/round: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "stream", | |
| "text": [ | |
| "Epoch 1/2\n", | |
| "782/782 [==============================] - 23s 29ms/step - loss: 1.5063 - accuracy: 0.4414 - val_loss: 2.0971 - val_accuracy: 0.2783\n", | |
| "Epoch 2/2\n", | |
| "782/782 [==============================] - 19s 24ms/step - loss: 1.0531 - accuracy: 0.6293 - val_loss: 1.6104 - val_accuracy: 0.4600\n" | |
| ], | |
| "name": "stdout" | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#4527A0\"><h1 style=\"font-size:18px\">Trial complete</h1></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#4527A0\"><h1 style=\"font-size:18px\">Trial summary</h1></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Trial ID: 5b26563c42e9cd59aff43a19815d2f66</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Score: 0.46000000834465027</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Best step: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">Hyperparameters:</h2></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-conv_blocks: 3</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-dropout: 0.4</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-filters_0: 128</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-filters_1: 128</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-filters_2: 32</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-filters_3: 192</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-filters_4: 96</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-hidden_size: 60</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-learning_rate: 0.002690251865167887</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-pooling_0: max</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-pooling_1: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-pooling_2: max</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-pooling_3: max</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-pooling_4: max</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-tuner/bracket: 3</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-tuner/epochs: 2</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-tuner/initial_epoch: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-tuner/round: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "stream", | |
| "text": [ | |
| "Epoch 1/2\n", | |
| "782/782 [==============================] - 20s 25ms/step - loss: 1.5149 - accuracy: 0.4447 - val_loss: 2.0766 - val_accuracy: 0.3624\n", | |
| "Epoch 2/2\n", | |
| "782/782 [==============================] - 16s 21ms/step - loss: 1.0535 - accuracy: 0.6302 - val_loss: 1.3861 - val_accuracy: 0.5562\n" | |
| ], | |
| "name": "stdout" | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#4527A0\"><h1 style=\"font-size:18px\">Trial complete</h1></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#4527A0\"><h1 style=\"font-size:18px\">Trial summary</h1></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Trial ID: 581503263c5c2572abc1f8c7a056b976</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Score: 0.5562000274658203</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Best step: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">Hyperparameters:</h2></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-conv_blocks: 4</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-dropout: 0.30000000000000004</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-filters_0: 64</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-filters_1: 160</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-filters_2: 64</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-filters_3: 224</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-filters_4: 96</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-hidden_size: 100</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-learning_rate: 0.002912198883472173</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-pooling_0: max</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-pooling_1: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-pooling_2: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-pooling_3: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-pooling_4: max</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-tuner/bracket: 3</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-tuner/epochs: 2</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-tuner/initial_epoch: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-tuner/round: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "stream", | |
| "text": [ | |
| "Epoch 1/2\n", | |
| "782/782 [==============================] - 37s 48ms/step - loss: 1.5409 - accuracy: 0.4552 - val_loss: 1.3689 - val_accuracy: 0.5155\n", | |
| "Epoch 2/2\n", | |
| "782/782 [==============================] - 34s 44ms/step - loss: 1.0119 - accuracy: 0.6598 - val_loss: 0.9049 - val_accuracy: 0.6785\n" | |
| ], | |
| "name": "stdout" | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#4527A0\"><h1 style=\"font-size:18px\">Trial complete</h1></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#4527A0\"><h1 style=\"font-size:18px\">Trial summary</h1></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Trial ID: c534255de19cbf7adef3727004515c31</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Score: 0.6784999966621399</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Best step: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">Hyperparameters:</h2></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-conv_blocks: 4</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-dropout: 0.5</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-filters_0: 224</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-filters_1: 64</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-filters_2: 224</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-filters_3: 192</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-filters_4: 224</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-hidden_size: 60</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-learning_rate: 0.0007847228772553556</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-pooling_0: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-pooling_1: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-pooling_2: max</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-pooling_3: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-pooling_4: max</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-tuner/bracket: 3</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-tuner/epochs: 2</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-tuner/initial_epoch: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-tuner/round: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "stream", | |
| "text": [ | |
| "Epoch 1/2\n", | |
| "782/782 [==============================] - 38s 48ms/step - loss: 1.9524 - accuracy: 0.2227 - val_loss: 2.0383 - val_accuracy: 0.1904\n", | |
| "Epoch 2/2\n", | |
| "782/782 [==============================] - 35s 44ms/step - loss: 1.7501 - accuracy: 0.3090 - val_loss: 2.7663 - val_accuracy: 0.2362\n" | |
| ], | |
| "name": "stdout" | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#4527A0\"><h1 style=\"font-size:18px\">Trial complete</h1></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#4527A0\"><h1 style=\"font-size:18px\">Trial summary</h1></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Trial ID: 6f7128471f87594a4c8b6673f85067ed</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Score: 0.2362000048160553</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Best step: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">Hyperparameters:</h2></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-conv_blocks: 5</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-dropout: 0.2</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-filters_0: 224</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-filters_1: 64</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-filters_2: 192</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-filters_3: 224</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-filters_4: 224</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-hidden_size: 90</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-learning_rate: 0.007747324188069747</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-pooling_0: max</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-pooling_1: max</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-pooling_2: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-pooling_3: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-pooling_4: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-tuner/bracket: 3</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-tuner/epochs: 2</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-tuner/initial_epoch: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-tuner/round: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "stream", | |
| "text": [ | |
| "Epoch 1/2\n", | |
| "782/782 [==============================] - 17s 22ms/step - loss: 1.3549 - accuracy: 0.5179 - val_loss: 1.5829 - val_accuracy: 0.4902\n", | |
| "Epoch 2/2\n", | |
| "782/782 [==============================] - 13s 16ms/step - loss: 0.8755 - accuracy: 0.7020 - val_loss: 0.8117 - val_accuracy: 0.7195\n" | |
| ], | |
| "name": "stdout" | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#4527A0\"><h1 style=\"font-size:18px\">Trial complete</h1></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#4527A0\"><h1 style=\"font-size:18px\">Trial summary</h1></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Trial ID: 7ceb4e994e077e54ed4c3170431675af</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Score: 0.7195000052452087</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Best step: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">Hyperparameters:</h2></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-conv_blocks: 5</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-dropout: 0.30000000000000004</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-filters_0: 32</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-filters_1: 128</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-filters_2: 160</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-filters_3: 128</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-filters_4: 160</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-hidden_size: 80</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-learning_rate: 0.0003135960216764952</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-pooling_0: max</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-pooling_1: max</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-pooling_2: max</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-pooling_3: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-pooling_4: max</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-tuner/bracket: 3</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-tuner/epochs: 2</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-tuner/initial_epoch: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-tuner/round: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "stream", | |
| "text": [ | |
| "Epoch 1/2\n", | |
| "782/782 [==============================] - 45s 57ms/step - loss: 2.0812 - accuracy: 0.1709 - val_loss: 2.0347 - val_accuracy: 0.1919\n", | |
| "Epoch 2/2\n", | |
| "782/782 [==============================] - 42s 54ms/step - loss: 1.9160 - accuracy: 0.2260 - val_loss: 1.9013 - val_accuracy: 0.2561\n" | |
| ], | |
| "name": "stdout" | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#4527A0\"><h1 style=\"font-size:18px\">Trial complete</h1></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#4527A0\"><h1 style=\"font-size:18px\">Trial summary</h1></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Trial ID: 6e2a71d2385ba5257107d773d4b009a7</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Score: 0.25609999895095825</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-Best step: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:#7E57C2\"><h2 style=\"font-size:16px\">Hyperparameters:</h2></span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-conv_blocks: 4</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-dropout: 0.5</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-filters_0: 224</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-filters_1: 256</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-filters_2: 160</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-filters_3: 192</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-filters_4: 64</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-hidden_size: 70</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-learning_rate: 0.008672607039556027</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-pooling_0: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-pooling_1: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-pooling_2: avg</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-pooling_3: max</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-pooling_4: max</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-tuner/bracket: 3</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-tuner/epochs: 2</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:cyan\"> |-tuner/initial_epoch: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<span style=\"color:blue\"> |-tuner/round: 0</span>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "stream", | |
| "text": [ | |
| "Epoch 1/2\n", | |
| " 167/UnknownBuffered data was truncated after reaching the output size limit." | |
| ], | |
| "name": "stdout" | |
| } | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "9z4P0LQxcbii", | |
| "colab_type": "code", | |
| "colab": {} | |
| }, | |
| "source": [ | |
| "best_model = tuner.get_best_models(1)[0]" | |
| ], | |
| "execution_count": 0, | |
| "outputs": [] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "mAgrvinVcfhZ", | |
| "colab_type": "code", | |
| "colab": {} | |
| }, | |
| "source": [ | |
| "best_hyperparameters = tuner.get_best_hyperparameters(1)[0]" | |
| ], | |
| "execution_count": 0, | |
| "outputs": [] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "8p6pWYhKJ-UK", | |
| "colab_type": "code", | |
| "colab": { | |
| "base_uri": "https://localhost:8080/", | |
| "height": 1000 | |
| }, | |
| "outputId": "f354e5ae-94d6-4567-b450-61252e8bf51f" | |
| }, | |
| "source": [ | |
| "best_model.summary()" | |
| ], | |
| "execution_count": 34, | |
| "outputs": [ | |
| { | |
| "output_type": "stream", | |
| "text": [ | |
| "Model: \"model\"\n", | |
| "_________________________________________________________________\n", | |
| "Layer (type) Output Shape Param # \n", | |
| "=================================================================\n", | |
| "input_1 (InputLayer) [(None, 32, 32, 3)] 0 \n", | |
| "_________________________________________________________________\n", | |
| "conv2d (Conv2D) (None, 32, 32, 256) 7168 \n", | |
| "_________________________________________________________________\n", | |
| "batch_normalization (BatchNo (None, 32, 32, 256) 1024 \n", | |
| "_________________________________________________________________\n", | |
| "re_lu (ReLU) (None, 32, 32, 256) 0 \n", | |
| "_________________________________________________________________\n", | |
| "conv2d_1 (Conv2D) (None, 32, 32, 256) 590080 \n", | |
| "_________________________________________________________________\n", | |
| "batch_normalization_1 (Batch (None, 32, 32, 256) 1024 \n", | |
| "_________________________________________________________________\n", | |
| "re_lu_1 (ReLU) (None, 32, 32, 256) 0 \n", | |
| "_________________________________________________________________\n", | |
| "average_pooling2d (AveragePo (None, 16, 16, 256) 0 \n", | |
| "_________________________________________________________________\n", | |
| "conv2d_2 (Conv2D) (None, 16, 16, 160) 368800 \n", | |
| "_________________________________________________________________\n", | |
| "batch_normalization_2 (Batch (None, 16, 16, 160) 640 \n", | |
| "_________________________________________________________________\n", | |
| "re_lu_2 (ReLU) (None, 16, 16, 160) 0 \n", | |
| "_________________________________________________________________\n", | |
| "conv2d_3 (Conv2D) (None, 16, 16, 160) 230560 \n", | |
| "_________________________________________________________________\n", | |
| "batch_normalization_3 (Batch (None, 16, 16, 160) 640 \n", | |
| "_________________________________________________________________\n", | |
| "re_lu_3 (ReLU) (None, 16, 16, 160) 0 \n", | |
| "_________________________________________________________________\n", | |
| "max_pooling2d (MaxPooling2D) (None, 8, 8, 160) 0 \n", | |
| "_________________________________________________________________\n", | |
| "conv2d_4 (Conv2D) (None, 8, 8, 256) 368896 \n", | |
| "_________________________________________________________________\n", | |
| "batch_normalization_4 (Batch (None, 8, 8, 256) 1024 \n", | |
| "_________________________________________________________________\n", | |
| "re_lu_4 (ReLU) (None, 8, 8, 256) 0 \n", | |
| "_________________________________________________________________\n", | |
| "conv2d_5 (Conv2D) (None, 8, 8, 256) 590080 \n", | |
| "_________________________________________________________________\n", | |
| "batch_normalization_5 (Batch (None, 8, 8, 256) 1024 \n", | |
| "_________________________________________________________________\n", | |
| "re_lu_5 (ReLU) (None, 8, 8, 256) 0 \n", | |
| "_________________________________________________________________\n", | |
| "average_pooling2d_1 (Average (None, 4, 4, 256) 0 \n", | |
| "_________________________________________________________________\n", | |
| "conv2d_6 (Conv2D) (None, 4, 4, 224) 516320 \n", | |
| "_________________________________________________________________\n", | |
| "batch_normalization_6 (Batch (None, 4, 4, 224) 896 \n", | |
| "_________________________________________________________________\n", | |
| "re_lu_6 (ReLU) (None, 4, 4, 224) 0 \n", | |
| "_________________________________________________________________\n", | |
| "conv2d_7 (Conv2D) (None, 4, 4, 224) 451808 \n", | |
| "_________________________________________________________________\n", | |
| "batch_normalization_7 (Batch (None, 4, 4, 224) 896 \n", | |
| "_________________________________________________________________\n", | |
| "re_lu_7 (ReLU) (None, 4, 4, 224) 0 \n", | |
| "_________________________________________________________________\n", | |
| "max_pooling2d_1 (MaxPooling2 (None, 2, 2, 224) 0 \n", | |
| "_________________________________________________________________\n", | |
| "global_average_pooling2d (Gl (None, 224) 0 \n", | |
| "_________________________________________________________________\n", | |
| "dense (Dense) (None, 50) 11250 \n", | |
| "_________________________________________________________________\n", | |
| "dropout (Dropout) (None, 50) 0 \n", | |
| "_________________________________________________________________\n", | |
| "dense_1 (Dense) (None, 10) 510 \n", | |
| "=================================================================\n", | |
| "Total params: 3,142,640\n", | |
| "Trainable params: 3,139,056\n", | |
| "Non-trainable params: 3,584\n", | |
| "_________________________________________________________________\n" | |
| ], | |
| "name": "stdout" | |
| } | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "Etnig-gyKObh", | |
| "colab_type": "code", | |
| "colab": { | |
| "base_uri": "https://localhost:8080/", | |
| "height": 352 | |
| }, | |
| "outputId": "59e02320-fb9f-4f1b-949c-f6a91f03ef2d" | |
| }, | |
| "source": [ | |
| "best_hyperparameters.values" | |
| ], | |
| "execution_count": 37, | |
| "outputs": [ | |
| { | |
| "output_type": "execute_result", | |
| "data": { | |
| "text/plain": [ | |
| "{'conv_blocks': 4,\n", | |
| " 'dropout': 0.30000000000000004,\n", | |
| " 'filters_0': 256,\n", | |
| " 'filters_1': 160,\n", | |
| " 'filters_2': 256,\n", | |
| " 'filters_3': 224,\n", | |
| " 'filters_4': 192,\n", | |
| " 'hidden_size': 50,\n", | |
| " 'learning_rate': 0.0004226668692674324,\n", | |
| " 'pooling_0': 'avg',\n", | |
| " 'pooling_1': 'max',\n", | |
| " 'pooling_2': 'avg',\n", | |
| " 'pooling_3': 'max',\n", | |
| " 'pooling_4': 'avg',\n", | |
| " 'tuner/bracket': 2,\n", | |
| " 'tuner/epochs': 10,\n", | |
| " 'tuner/initial_epoch': 4,\n", | |
| " 'tuner/round': 1,\n", | |
| " 'tuner/trial_id': '3fad98f9d2065dc54df805781c735408'}" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| }, | |
| "execution_count": 37 | |
| } | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "h-I_YO7PLP2P", | |
| "colab_type": "code", | |
| "colab": { | |
| "base_uri": "https://localhost:8080/", | |
| "height": 54 | |
| }, | |
| "outputId": "cd9886dd-1d21-44c0-ee24-44eba1b812c0" | |
| }, | |
| "source": [ | |
| "best_model.metrics_names" | |
| ], | |
| "execution_count": 38, | |
| "outputs": [ | |
| { | |
| "output_type": "execute_result", | |
| "data": { | |
| "text/plain": [ | |
| "['loss', 'accuracy']" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| }, | |
| "execution_count": 38 | |
| } | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "zzwfYWBXtvmq", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "[](https://www.backprop.fr)" | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "4ULD8LNntZWj", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "## <font color=\"teal\">Built-in Tunable Models</font>" | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "Xse2LXqItcbJ", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "In addition to allowing you to define your own tunable models, Keras Tuner provides two built-in tunable models: HyperResnet and HyperXception. These models search over various permutations of the ResNet and Xception architectures, respectively. These models can be used with a Tuner like this:" | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "ed8YjFnwuu8M", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "Voir [ici](https://blog.tensorflow.org/2020/01/hyperparameter-tuning-with-keras-tuner.html?linkId=81371017)" | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "dzagiMJhtyCq", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "[](https://www.backprop.fr)" | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "9C7HkEgVt31Z", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "## <font color=\"teal\">Distributed Tuning</font>" | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "96u7W4P8t7fU", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "With Keras Tuner, you can do both data-parallel and trial-parallel distribution. That is, you can use tf.distribute.Strategy to run each Model on multiple GPUs, and you can also search over multiple different hyperparameter combinations in parallel on different workers. \n", | |
| "\n", | |
| "No code changes are needed to perform a trial-parallel search. Simply set the KERASTUNER_TUNER_ID, KERASTUNER_ORACLE_IP, and KERASTUNER_ORACLE_PORT environment variables, for example as shown in the bash script here:" | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "d6CruynjusaS", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "Voir [ici](https://blog.tensorflow.org/2020/01/hyperparameter-tuning-with-keras-tuner.html?linkId=81371017)" | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "PPTF5h1Mt-Z8", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "## <font color=\"teal\">Custom Training Loops</font>" | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "55F5C0-suKA-", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "The `kerastuner.Tuner` class can be subclassed to support advanced uses such as:\n", | |
| "Custom training loops (GANs, reinforcement learning, etc.)\n", | |
| "Adding hyperparameters outside of the model building function (preprocessing, data augmentation, test time augmentation, etc.)\n", | |
| "Here’s a simple example:" | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "pq2X6ejnurIy", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "Voir [ici](https://blog.tensorflow.org/2020/01/hyperparameter-tuning-with-keras-tuner.html?linkId=81371017)" | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "AOiGkscUubIM", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "## <font color=\"teal\">Tuning Scikit-learn Models</font>" | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "aIXBlMSKufsU", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "Despite its name, Keras Tuner can be used to tune a wide variety of machine learning models. In addition to built-in Tuners for Keras models, Keras Tuner provides a built-in Tuner that works with Scikit-learn models. Here’s a simple example of how to use this tuner:" | |
| ] | |
| }, | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "fI9ZMtQ_unkB", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "Voir [ici](https://blog.tensorflow.org/2020/01/hyperparameter-tuning-with-keras-tuner.html?linkId=81371017)" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "W8H6R91UuOJr", | |
| "colab_type": "code", | |
| "colab": {} | |
| }, | |
| "source": [ | |
| "" | |
| ], | |
| "execution_count": 0, | |
| "outputs": [] | |
| } | |
| ] | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment