{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"provenance": []
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
}
},
"cells": [
{
"cell_type": "markdown",
"source": [
"#Perform a practical CNN algorithm."
],
"metadata": {
"id": "nJZv4-_T2ZwI"
}
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "a8e64375",
"outputId": "d3fcf41b-6be9-4572-ebac-deb203796ca1"
},
"source": [
"import tensorflow as tf\n",
"from tensorflow.keras.datasets import mnist\n",
"from tensorflow.keras.utils import to_categorical\n",
"\n",
"# Load the MNIST dataset\n",
"(x_train, y_train), (x_test, y_test) = mnist.load_data()\n",
"\n",
"# Preprocess the data\n",
"# Reshape data to include channel dimension\n",
"x_train = x_train.reshape(x_train.shape[0], 28, 28, 1).astype('float32')\n",
"x_test = x_test.reshape(x_test.shape[0], 28, 28, 1).astype('float32')\n",
"\n",
"# Normalize pixel values to be between 0 and 1\n",
"x_train = x_train / 255\n",
"x_test = x_test / 255\n",
"\n",
"# Convert labels to one-hot encoding\n",
"y_train = to_categorical(y_train)\n",
"y_test = to_categorical(y_test)\n",
"\n",
"print(\"Data loaded and preprocessed successfully!\")\n",
"print(\"x_train shape:\", x_train.shape)\n",
"print(\"y_train shape:\", y_train.shape)\n",
"print(\"x_test shape:\", x_test.shape)\n",
"print(\"y_test shape:\", y_test.shape)"
],
"execution_count": 1,
"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",
"Data loaded and preprocessed successfully!\n",
"x_train shape: (60000, 28, 28, 1)\n",
"y_train shape: (60000, 10)\n",
"x_test shape: (10000, 28, 28, 1)\n",
"y_test shape: (10000, 10)\n"
]
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 408
},
"id": "037f7d14",
"outputId": "fbdc3901-d48a-4dab-be89-f924f56597bb"
},
"source": [
"from tensorflow.keras.models import Sequential\n",
"from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense\n",
"\n",
"# Build the CNN model\n",
"model = Sequential([\n",
" Conv2D(32, kernel_size=(3, 3), activation='relu', input_shape=(28, 28, 1)),\n",
" MaxPooling2D(pool_size=(2, 2)),\n",
" Conv2D(64, kernel_size=(3, 3), activation='relu'),\n",
" MaxPooling2D(pool_size=(2, 2)),\n",
" Flatten(),\n",
" Dense(128, activation='relu'),\n",
" Dense(10, activation='softmax') # 10 output classes for MNIST\n",
"])\n",
"\n",
"model.summary()"
],
"execution_count": 2,
"outputs": [
{
"output_type": "stream",
"name": "stderr",
"text": [
"/usr/local/lib/python3.12/dist-packages/keras/src/layers/convolutional/base_conv.py:113: 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"
]
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"\u001b[1mModel: \"sequential\"\u001b[0m\n"
],
"text/html": [
"Model: \"sequential\"\n",
"\n"
]
},
"metadata": {}
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
"┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\n",
"┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
"│ conv2d (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m26\u001b[0m, \u001b[38;5;34m26\u001b[0m, \u001b[38;5;34m32\u001b[0m) │ \u001b[38;5;34m320\u001b[0m │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ max_pooling2d (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m13\u001b[0m, \u001b[38;5;34m13\u001b[0m, \u001b[38;5;34m32\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ conv2d_1 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m11\u001b[0m, \u001b[38;5;34m11\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m18,496\u001b[0m │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ max_pooling2d_1 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m5\u001b[0m, \u001b[38;5;34m5\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ flatten (\u001b[38;5;33mFlatten\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1600\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ dense (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m204,928\u001b[0m │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ dense_1 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m10\u001b[0m) │ \u001b[38;5;34m1,290\u001b[0m │\n",
"└─────────────────────────────────┴────────────────────────┴───────────────┘\n"
],
"text/html": [
"┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
"┃ Layer (type) ┃ Output Shape ┃ Param # ┃\n",
"┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
"│ conv2d (Conv2D) │ (None, 26, 26, 32) │ 320 │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ max_pooling2d (MaxPooling2D) │ (None, 13, 13, 32) │ 0 │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ conv2d_1 (Conv2D) │ (None, 11, 11, 64) │ 18,496 │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ max_pooling2d_1 (MaxPooling2D) │ (None, 5, 5, 64) │ 0 │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ flatten (Flatten) │ (None, 1600) │ 0 │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ dense (Dense) │ (None, 128) │ 204,928 │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ dense_1 (Dense) │ (None, 10) │ 1,290 │\n",
"└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
"\n"
]
},
"metadata": {}
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"\u001b[1m Total params: \u001b[0m\u001b[38;5;34m225,034\u001b[0m (879.04 KB)\n"
],
"text/html": [
" Total params: 225,034 (879.04 KB)\n",
"\n"
]
},
"metadata": {}
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m225,034\u001b[0m (879.04 KB)\n"
],
"text/html": [
" Trainable params: 225,034 (879.04 KB)\n",
"\n"
]
},
"metadata": {}
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
],
"text/html": [
" Non-trainable params: 0 (0.00 B)\n",
"\n"
]
},
"metadata": {}
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "5481c528",
"outputId": "19ee72af-b717-483f-cf61-ca38f755d7b0"
},
"source": [
"# Compile the model\n",
"model.compile(optimizer='adam',\n",
" loss='categorical_crossentropy',\n",
" metrics=['accuracy'])\n",
"\n",
"# Train the model\n",
"history = model.fit(x_train, y_train,\n",
" epochs=10, # You can adjust the number of epochs\n",
" batch_size=32, # You can adjust the batch size\n",
" validation_split=0.1) # Using a validation split to monitor performance during training"
],
"execution_count": 3,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Epoch 1/10\n",
"\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m50s\u001b[0m 29ms/step - accuracy: 0.9031 - loss: 0.3098 - val_accuracy: 0.9878 - val_loss: 0.0427\n",
"Epoch 2/10\n",
"\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m80s\u001b[0m 28ms/step - accuracy: 0.9856 - loss: 0.0474 - val_accuracy: 0.9880 - val_loss: 0.0442\n",
"Epoch 3/10\n",
"\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m84s\u001b[0m 29ms/step - accuracy: 0.9906 - loss: 0.0298 - val_accuracy: 0.9915 - val_loss: 0.0310\n",
"Epoch 4/10\n",
"\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m81s\u001b[0m 29ms/step - accuracy: 0.9938 - loss: 0.0180 - val_accuracy: 0.9910 - val_loss: 0.0359\n",
"Epoch 5/10\n",
"\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m47s\u001b[0m 28ms/step - accuracy: 0.9960 - loss: 0.0140 - val_accuracy: 0.9913 - val_loss: 0.0369\n",
"Epoch 6/10\n",
"\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m84s\u001b[0m 29ms/step - accuracy: 0.9969 - loss: 0.0100 - val_accuracy: 0.9898 - val_loss: 0.0401\n",
"Epoch 7/10\n",
"\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m82s\u001b[0m 29ms/step - accuracy: 0.9970 - loss: 0.0094 - val_accuracy: 0.9915 - val_loss: 0.0418\n",
"Epoch 8/10\n",
"\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m81s\u001b[0m 28ms/step - accuracy: 0.9975 - loss: 0.0074 - val_accuracy: 0.9895 - val_loss: 0.0434\n",
"Epoch 9/10\n",
"\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m83s\u001b[0m 29ms/step - accuracy: 0.9982 - loss: 0.0057 - val_accuracy: 0.9908 - val_loss: 0.0429\n",
"Epoch 10/10\n",
"\u001b[1m1688/1688\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m82s\u001b[0m 29ms/step - accuracy: 0.9977 - loss: 0.0059 - val_accuracy: 0.9908 - val_loss: 0.0465\n"
]
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "bd9794d1",
"outputId": "ce929ed0-fd36-4bc3-8b7f-99d4ce014e21"
},
"source": [
"# Evaluate the model\n",
"loss, accuracy = model.evaluate(x_test, y_test, verbose=0)\n",
"\n",
"print(f\"Test Loss: {loss:.4f}\")\n",
"print(f\"Test Accuracy: {accuracy:.4f}\")"
],
"execution_count": 4,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Test Loss: 0.0408\n",
"Test Accuracy: 0.9905\n"
]
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 348
},
"id": "cd8d1c0b",
"outputId": "5a86ec6f-82c0-48f1-8cd6-645eb7842699"
},
"source": [
"import matplotlib.pyplot as plt\n",
"\n",
"# Plot training and validation accuracy\n",
"plt.figure(figsize=(12, 4))\n",
"plt.subplot(1, 2, 1)\n",
"plt.plot(history.history['accuracy'], label='Training Accuracy')\n",
"plt.plot(history.history['val_accuracy'], label='Validation Accuracy')\n",
"plt.title('Training and Validation Accuracy')\n",
"plt.xlabel('Epoch')\n",
"plt.ylabel('Accuracy')\n",
"plt.legend()\n",
"\n",
"# Plot training and validation loss\n",
"plt.subplot(1, 2, 2)\n",
"plt.plot(history.history['loss'], label='Training Loss')\n",
"plt.plot(history.history['val_loss'], label='Validation Loss')\n",
"plt.title('Training and Validation Loss')\n",
"plt.xlabel('Epoch')\n",
"plt.ylabel('Loss')\n",
"plt.legend()\n",
"\n",
"plt.show()"
],
"execution_count": 5,
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
""
],
"image/png": "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\n"
},
"metadata": {}
}
]
}
]
}