{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "code",
      "source": [
        "# Description: This program use Convolutional Neural Networks(CNN)\n",
        "#              classify handwritten digits as number 0-9"
      ],
      "metadata": {
        "id": "aG9gtI4ILjw7"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "#importing the libraries\n",
        "from keras.models import Sequential\n",
        "from keras.layers import Dense, Conv2D, Flatten, MaxPool2D\n",
        "from keras.datasets import mnist\n",
        "from keras.utils import to_categorical\n",
        "import numpy as np\n",
        "import matplotlib.pyplot as plt"
      ],
      "metadata": {
        "id": "88xMcxjMLrhq"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Importing necessary libraries\n",
        "from keras.datasets import mnist  # Ensure this import is present\n",
        "\n",
        "# Load the data and split it into train and test\n",
        "(X_train, y_train), (X_test, y_test) = mnist.load_data()\n",
        "\n",
        "# Print the shape of the data to confirm it is loaded correctly\n",
        "print(X_train.shape)\n",
        "print(X_test.shape)\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "NWxxlIBWLwnS",
        "outputId": "8d4d841a-da0c-450a-ba2a-eedb569143eb"
      },
      "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[1m1s\u001b[0m 0us/step\n",
            "(60000, 28, 28)\n",
            "(10000, 28, 28)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import matplotlib.pyplot as plt\n",
        "plt.imshow(X_train[2])"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 448
        },
        "id": "E9KENPZLMPic",
        "outputId": "1270dab9-963a-4c5a-c341-a6c9c953aaf7"
      },
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<matplotlib.image.AxesImage at 0x7fbaa2f2ece0>"
            ]
          },
          "metadata": {},
          "execution_count": 4
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Reshaping the data to fit the model\n",
        "X_train = X_train.reshape(60000, 28, 28, 1)\n",
        "X_test = X_test.reshape(10000, 28, 28, 1)\n",
        ""
      ],
      "metadata": {
        "id": "T9QNOCA-MUza"
      },
      "execution_count": 5,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from keras.utils import to_categorical\n",
        "# One-Hot Encoding:\n",
        "y_train_one_hot = to_categorical(y_train)\n",
        "y_test_one_hot = to_categorical(y_test)\n",
        "\n",
        "# Print the new label\n",
        "print(y_train_one_hot[0])\n",
        ""
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "_dz47ah6Mbxb",
        "outputId": "07e352a8-70e8-4ade-9276-d25590d644ec"
      },
      "execution_count": 7,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "[0. 0. 0. 0. 0. 1. 0. 0. 0. 0.]\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from keras.models import Sequential\n",
        "from keras.layers import Dense, Conv2D, Flatten, MaxPool2D\n",
        "# Build the CNN model\n",
        "model = Sequential()\n",
        "# Add model layers\n",
        "model.add(Conv2D(64, kernel_size=3, activation = 'relu', input_shape=(28,28,1)))\n",
        "model.add(Conv2D(32, kernel_size=3, activation='relu'))\n",
        "model.add(MaxPool2D(pool_size=(2, 2), strides=None, padding='valid', data_format=None))\n",
        "model.add(Flatten())\n",
        "model.add(Dense(10,activation='softmax'))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "2IMtu7wBMl1y",
        "outputId": "ae139133-66e6-410c-f683-15dbb934435b"
      },
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.10/dist-packages/keras/src/layers/convolutional/base_conv.py:107: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
            "  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])"
      ],
      "metadata": {
        "id": "McSShYa9Mxoq"
      },
      "execution_count": 11,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "#Train the model\n",
        "hist = model.fit(X_train,y_train_one_hot, validation_data=(X_test,y_test_one_hot), epochs=3)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "VIpA9GLFNvwS",
        "outputId": "64c9c7d0-2466-4017-bb9c-b1b2c754ea55"
      },
      "execution_count": 14,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/3\n",
            "\u001b[1m1875/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m150s\u001b[0m 80ms/step - accuracy: 0.9793 - loss: 0.0654 - val_accuracy: 0.9801 - val_loss: 0.0650\n",
            "Epoch 2/3\n",
            "\u001b[1m1875/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m157s\u001b[0m 84ms/step - accuracy: 0.9851 - loss: 0.0480 - val_accuracy: 0.9798 - val_loss: 0.0742\n",
            "Epoch 3/3\n",
            "\u001b[1m1875/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m198s\u001b[0m 81ms/step - accuracy: 0.9885 - loss: 0.0370 - val_accuracy: 0.9814 - val_loss: 0.0669\n"
          ]
        }
      ]
    }
  ]
}