TF_Forum_53230.ipynb

tf_forum_53230.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "authorship_tag": "ABX9TyPrsik1ULc5MzXHkLI4cUlt",
      "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/f560548016e5227633647f967051398d/tf_forum_53230.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": "TgVqDnw70c3b"
      },
      "outputs": [],
      "source": [
        "import tensorflow as tf\n",
        "import keras\n",
        "import numpy as np"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "mnist=keras.datasets.mnist.load_data()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "fHIM9Rzu0jXB",
        "outputId": "7d95e3ec-a9fb-4f5d-f699-6d2a91ae00e9"
      },
      "execution_count": 2,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/mnist.npz\n",
            "\u001b[1m11490434/11490434\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 0us/step\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "(x_train,y_train),(x_test,y_test)=mnist"
      ],
      "metadata": {
        "id": "7wpn8-6T0lGm"
      },
      "execution_count": 3,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "x_train=x_train.astype('float32')/255\n",
        "x_test=x_test.astype('float32')/255"
      ],
      "metadata": {
        "id": "cHsvwC5R0m4x"
      },
      "execution_count": 4,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "y_train=keras.utils.to_categorical(y_train,10)\n",
        "y_test=keras.utils.to_categorical(y_test,10)"
      ],
      "metadata": {
        "id": "YIkk9k3H0opj"
      },
      "execution_count": 5,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from keras import activations"
      ],
      "metadata": {
        "id": "ZgFK1Z9T0qeb"
      },
      "execution_count": 6,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "model=keras.Sequential([\n",
        "                        keras.Input(shape=(28,28,1)),\n",
        "                        keras.layers.Conv2D(32,kernel_size=(3,3),activation='relu',),\n",
        "                        keras.layers.MaxPooling2D(pool_size=(2,2)),\n",
        "                        keras.layers.Conv2D(64,kernel_size=(3,3),activation='relu'),\n",
        "                        keras.layers.MaxPooling2D(pool_size=(2,2)),\n",
        "                        keras.layers.GlobalAveragePooling2D(),\n",
        "                        keras.layers.Dropout(0.5),\n",
        "                        keras.layers.Dense(10),\n",
        "                        keras.layers.Activation(activations.softmax)\n",
        "])"
      ],
      "metadata": {
        "id": "TevJaA9B0s0T"
      },
      "execution_count": 7,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "optimizer=tf.keras.optimizers.Adam()"
      ],
      "metadata": {
        "id": "kP5yH8lE0uY_"
      },
      "execution_count": 8,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "model.compile(loss=\"categorical_crossentropy\", optimizer=optimizer,metrics=['accuracy'])"
      ],
      "metadata": {
        "id": "UYw1wJex0wOK"
      },
      "execution_count": 9,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "model.fit(x_train,y_train,epochs=2)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "JlUoFbHG0yBw",
        "outputId": "5b311bbe-d080-49cd-d7d5-6b45e7ea43e5"
      },
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/2\n",
            "\u001b[1m1875/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m56s\u001b[0m 29ms/step - accuracy: 0.3622 - loss: 1.7816\n",
            "Epoch 2/2\n",
            "\u001b[1m1875/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m85s\u001b[0m 30ms/step - accuracy: 0.7221 - loss: 0.8613\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<keras.src.callbacks.history.History at 0x7cbdc341e8c0>"
            ]
          },
          "metadata": {},
          "execution_count": 10
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "logits = model.predict(x_test)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "TJ29jZon00Lm",
        "outputId": "d4efd224-3522-40aa-d7dc-920d973386cd"
      },
      "execution_count": 11,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[1m313/313\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 15ms/step\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "logits[0]"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "RuTQV-Bb1Qt_",
        "outputId": "6fd9d7e9-4208-4909-b059-d4849115f8d8"
      },
      "execution_count": 12,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([2.7764330e-04, 9.4532346e-08, 2.8229714e-03, 1.0156622e-05,\n",
              "       1.4043928e-05, 5.8893958e-04, 5.5398455e-06, 9.7335368e-01,\n",
              "       4.8517436e-06, 2.2922000e-02], dtype=float32)"
            ]
          },
          "metadata": {},
          "execution_count": 12
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "sub_model = keras.Sequential(model.layers[:7])"
      ],
      "metadata": {
        "id": "z0AQof361RO1"
      },
      "execution_count": 13,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "x_test_ = tf.expand_dims(x_test, axis=-1)"
      ],
      "metadata": {
        "id": "XBAfjlLR1XYS"
      },
      "execution_count": 14,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "logits = sub_model.predict(x_test_)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Pn0s9k-E1bn4",
        "outputId": "4cb63591-fe15-4273-e888-482b59b0a001"
      },
      "execution_count": 15,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[1m313/313\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 11ms/step\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "logits[0]"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "mW2aGRCe1iji",
        "outputId": "7e902e00-52b1-43cb-c1dd-545d14b6bab4"
      },
      "execution_count": 16,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([ -2.173252  , -10.1584015 ,   0.14595598,  -5.481463  ,\n",
              "        -5.157399  ,  -1.4212654 ,  -6.087623  ,   5.9889135 ,\n",
              "        -6.220251  ,   2.2402632 ], dtype=float32)"
            ]
          },
          "metadata": {},
          "execution_count": 16
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "tf.nn.softmax(logits[0])"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ZNqTK98i1l5A",
        "outputId": "a8b305e5-933f-4285-d560-3232d2344028"
      },
      "execution_count": 17,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<tf.Tensor: shape=(10,), dtype=float32, numpy=\n",
              "array([2.7764330e-04, 9.4532354e-08, 2.8229717e-03, 1.0156622e-05,\n",
              "       1.4043929e-05, 5.8893964e-04, 5.5398459e-06, 9.7335374e-01,\n",
              "       4.8517441e-06, 2.2922002e-02], dtype=float32)>"
            ]
          },
          "metadata": {},
          "execution_count": 17
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "WEeFGO-41pJY"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}