SO_72380756.ipynb

so_72380756.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "SO_72380756.ipynb",
      "provenance": [],
      "authorship_tag": "ABX9TyM12NN63euwl47yS/9trhqm",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/gist/kiransair/8a1179ca68ca5243bff90c08b1df3bb9/so_72380756.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 1,
      "metadata": {
        "id": "RHH-xzJALo9g"
      },
      "outputs": [],
      "source": [
        "import tensorflow as tf"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "base_model = tf.keras.applications.Xception(\n",
        "    weights='imagenet',\n",
        "    # image shape = 128x128x3\n",
        "    input_shape=(128, 128, 3),\n",
        "    include_top=False)\n",
        "\n",
        "# freeze layers\n",
        "base_model.trainable = False\n",
        "\n",
        "inputs = tf.keras.Input(shape=(128, 128, 3))\n",
        "#x = data_augmentation(inputs)\n",
        "x = tf.keras.applications.xception.preprocess_input(inputs)\n",
        "x = base_model(x, training=False)\n",
        "x = tf.keras.layers.Flatten()(x)\n",
        "x = tf.keras.layers.Dense(128, activation='relu')(x) \n",
        "outputs = tf.keras.layers.Dense(1, activation='sigmoid')(x)\n",
        "model = tf.keras.Model(inputs, outputs)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Jtyi26vTLpcf",
        "outputId": "eeaa310a-337e-478f-c749-537dc5f7ad27"
      },
      "execution_count": 2,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Downloading data from https://storage.googleapis.com/tensorflow/keras-applications/xception/xception_weights_tf_dim_ordering_tf_kernels_notop.h5\n",
            "83689472/83683744 [==============================] - 1s 0us/step\n",
            "83697664/83683744 [==============================] - 1s 0us/step\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "x=tf.random.uniform(shape=(1,128,128,3))\n",
        "x= tf.keras.applications.xception.preprocess_input(x)                        "
      ],
      "metadata": {
        "id": "o3OXy9q9LrM7"
      },
      "execution_count": 3,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "theModel=tf.keras.models.Sequential([    \n",
        "   tf.keras.Input(tensor=x),\n",
        "   base_model,\n",
        "   tf.keras.layers.Flatten(),\n",
        "   tf.keras.layers.Dense(128, activation='relu'),\n",
        "   tf.keras.layers.Dense(1,activation='sigmoid')\n",
        "])"
      ],
      "metadata": {
        "id": "vXLH0VBVLs9S"
      },
      "execution_count": 4,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        ""
      ],
      "metadata": {
        "id": "3d3TKI8nLupy"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}