keras-tensorflow-problem.ipynb

untitled2.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "keras-tensorflow-problem.ipynb",
      "provenance": [],
      "authorship_tag": "ABX9TyMScnaczMGn1SWIP3CXA3VI",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/gist/fedxa/45eb1a412964ddf19820fff347c5b2de/untitled2.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "eyeh5WbCUMtw",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "# from keras.layers import Input, Dense\n",
        "# from keras.models import Model\n",
        "# from keras import regularizers\n",
        "from tensorflow.keras.layers import Input, Dense\n",
        "from tensorflow.keras.models import Model\n",
        "from tensorflow.keras import regularizers"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "2e-VxnQgUOT4",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "encoding_dim = 32  # 32 floats -> compression of factor 24.5, assuming the input is 784 floats\n",
        "\n",
        "input_img = Input(shape=(784,))\n",
        "# \"encoded\" is the encoded representation of the input\n",
        "encoded = Dense(encoding_dim, activation='relu')(input_img)\n",
        "# \"decoded\" is the lossy reconstruction of the input\n",
        "decoded = Dense(784, activation='sigmoid')(encoded)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "VX2PK92LUUVU",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "# this model maps an input to its reconstruction\n",
        "autoencoder = Model(input_img, decoded)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "-jTy_pn4UW21",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "# this model maps an input to its encoded representation\n",
        "encoder = Model(input_img, encoded)\n",
        "\n",
        "# create a placeholder for an encoded (32-dimensional) input\n",
        "encoded_input = Input(shape=(encoding_dim,))\n",
        "# retrieve the last layer of the autoencoder model\n",
        "decoder_layer = autoencoder.layers[-1]\n",
        "# create the decoder model\n",
        "decoder = Model(encoded_input, decoder_layer(encoded_input))"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "JvgM4lrqUaHz",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "autoencoder.compile(optimizer='adadelta', loss='binary_crossentropy')"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "hGB1kjdsUc36",
        "colab_type": "code",
        "outputId": "8bf4b87a-efcc-494f-f7da-0c6d1b823a5b",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 104
        }
      },
      "source": [
        "from keras.datasets import mnist\n",
        "import numpy as np\n",
        "(x_train, _), (x_test, _) = mnist.load_data()\n",
        "\n",
        "x_train = x_train.astype('float32') / 255.\n",
        "x_test = x_test.astype('float32') / 255.\n",
        "x_train = x_train.reshape((len(x_train), np.prod(x_train.shape[1:])))\n",
        "x_test = x_test.reshape((len(x_test), np.prod(x_test.shape[1:])))\n",
        "print(x_train.shape)\n",
        "print(x_test.shape)"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Downloading data from https://s3.amazonaws.com/img-datasets/mnist.npz\n",
            "\r    8192/11490434 [..............................] - ETA: 0s"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "Using TensorFlow backend.\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "stream",
          "text": [
            "11493376/11490434 [==============================] - 0s 0us/step\n",
            "(60000, 784)\n",
            "(10000, 784)\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "KPJYHADGUe1m",
        "colab_type": "code",
        "outputId": "20939fb0-a4b5-4266-a351-15c9251606e0",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 434
        }
      },
      "source": [
        "autoencoder.fit(x_train, x_train,\n",
        "                epochs=20,\n",
        "                batch_size=256,\n",
        "                shuffle=True,\n",
        "                validation_data=(x_test, x_test))"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Epoch 1/20\n",
            "235/235 [==============================] - 2s 10ms/step - loss: 0.6950 - val_loss: 0.6950\n",
            "Epoch 2/20\n",
            "235/235 [==============================] - 2s 10ms/step - loss: 0.6949 - val_loss: 0.6948\n",
            "Epoch 3/20\n",
            "235/235 [==============================] - 2s 10ms/step - loss: 0.6947 - val_loss: 0.6946\n",
            "Epoch 4/20\n",
            "235/235 [==============================] - 2s 10ms/step - loss: 0.6945 - val_loss: 0.6944\n",
            "Epoch 5/20\n",
            "235/235 [==============================] - 2s 10ms/step - loss: 0.6943 - val_loss: 0.6943\n",
            "Epoch 6/20\n",
            "235/235 [==============================] - 2s 10ms/step - loss: 0.6942 - val_loss: 0.6941\n",
            "Epoch 7/20\n",
            "235/235 [==============================] - 2s 10ms/step - loss: 0.6940 - val_loss: 0.6939\n",
            "Epoch 8/20\n",
            "235/235 [==============================] - 2s 10ms/step - loss: 0.6938 - val_loss: 0.6938\n",
            "Epoch 9/20\n",
            "235/235 [==============================] - 2s 10ms/step - loss: 0.6937 - val_loss: 0.6936\n",
            "Epoch 10/20\n",
            "235/235 [==============================] - 2s 10ms/step - loss: 0.6935 - val_loss: 0.6934\n",
            "Epoch 11/20\n",
            "235/235 [==============================] - 2s 10ms/step - loss: 0.6934 - val_loss: 0.6933\n",
            "Epoch 12/20\n",
            " 13/235 [>.............................] - ETA: 1s - loss: 0.6933"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "JaVPCf9NUhMb",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "# encode and decode some digits\n",
        "# note that we take them from the *test* set\n",
        "encoded_imgs = encoder.predict(x_test)\n",
        "decoded_imgs = decoder.predict(encoded_imgs)\n",
        "\n",
        "# use Matplotlib (don't ask)\n",
        "import matplotlib.pyplot as plt\n",
        "\n",
        "n = 10  # how many digits we will display\n",
        "plt.figure(figsize=(20, 4))\n",
        "for i in range(n):\n",
        "    # display original\n",
        "    ax = plt.subplot(2, n, i + 1)\n",
        "    plt.imshow(x_test[i].reshape(28, 28))\n",
        "    plt.gray()\n",
        "    ax.get_xaxis().set_visible(False)\n",
        "    ax.get_yaxis().set_visible(False)\n",
        "\n",
        "    # display reconstruction\n",
        "    ax = plt.subplot(2, n, i + 1 + n)\n",
        "    plt.imshow(decoded_imgs[i].reshape(28, 28))\n",
        "    plt.gray()\n",
        "    ax.get_xaxis().set_visible(False)\n",
        "    ax.get_yaxis().set_visible(False)\n",
        "plt.show()"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "DP8VznpQUklv",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        ""
      ],
      "execution_count": 0,
      "outputs": []
    }
  ]
}