{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# ML Practice Series: Module 24 - Deep Learning with TensorFlow/Keras\n",
"\n",
"Welcome to the world of modern **Deep Learning**! While we covered basic Neural Networks with Scikit-Learn, TensorFlow/Keras is the industry standard for building production-grade deep learning models.\n",
"\n",
"### Objectives:\n",
"1. **Sequential API**: Building neural networks layer by layer.\n",
"2. **Activations**: ReLU, Sigmoid, Softmax for different layers.\n",
"3. **Optimization**: Adam, SGD, Learning rate scheduling.\n",
"4. **Callbacks**: Early stopping and Model checkpointing.\n",
"5. **Computer Vision**: Building a CNN for image classification.\n",
"\n",
"---"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 1. Setup\n",
"We will use the **MNIST** dataset for handwritten digit classification."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"import tensorflow as tf\n",
"from tensorflow import keras\n",
"from tensorflow.keras import layers\n",
"\n",
"# Load MNIST\n",
"(X_train, y_train), (X_test, y_test) = keras.datasets.mnist.load_data()\n",
"\n",
"# Normalize to 0-1\n",
"X_train = X_train.astype('float32') / 255.0\n",
"X_test = X_test.astype('float32') / 255.0\n",
"\n",
"print(f\"Training shape: {X_train.shape}\")\n",
"print(f\"Test shape: {X_test.shape}\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 2. Building a Simple Neural Network\n",
"\n",
"### Task 1: Sequential Model\n",
"Create a Sequential model with:\n",
"1. Flatten layer (to convert 28x28 to 784)\n",
"2. Dense layer with 128 units and ReLU activation\n",
"3. Output Dense layer with 10 units and Softmax activation"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# YOUR CODE HERE"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"\n",
"Click to see Solution
\n",
"\n",
"```python\n",
"model = keras.Sequential([\n",
" layers.Flatten(input_shape=(28, 28)),\n",
" layers.Dense(128, activation='relu'),\n",
" layers.Dense(10, activation='softmax')\n",
"])\n",
"\n",
"model.summary()\n",
"```\n",
" "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 3. Compiling & Training\n",
"\n",
"### Task 2: Compile and Fit\n",
"Compile the model with:\n",
"- Optimizer: 'adam'\n",
"- Loss: 'sparse_categorical_crossentropy'\n",
"- Metrics: 'accuracy'\n",
"\n",
"Train for 5 epochs with a validation split of 0.2."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# YOUR CODE HERE"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"\n",
"Click to see Solution
\n",
"\n",
"```python\n",
"model.compile(\n",
" optimizer='adam',\n",
" loss='sparse_categorical_crossentropy',\n",
" metrics=['accuracy']\n",
")\n",
"\n",
"history = model.fit(\n",
" X_train, y_train,\n",
" epochs=5,\n",
" validation_split=0.2\n",
")\n",
"```\n",
" "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 4. Convolutional Neural Networks (CNN)\n",
"\n",
"### Task 3: Building a CNN\n",
"Create a CNN with:\n",
"1. Conv2D layer (32 filters, 3x3 kernel, ReLU)\n",
"2. MaxPooling2D (2x2)\n",
"3. Conv2D layer (64 filters, 3x3 kernel, ReLU)\n",
"4. MaxPooling2D (2x2)\n",
"5. Flatten\n",
"6. Dense (128, ReLU)\n",
"7. Dense (10, Softmax)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Reshape for CNN (add channel dimension)\n",
"X_train_cnn = X_train.reshape(-1, 28, 28, 1)\n",
"X_test_cnn = X_test.reshape(-1, 28, 28, 1)\n",
"\n",
"# YOUR CODE HERE"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"\n",
"Click to see Solution
\n",
"\n",
"```python\n",
"cnn_model = keras.Sequential([\n",
" layers.Conv2D(32, (3, 3), activation='relu', input_shape=(28, 28, 1)),\n",
" layers.MaxPooling2D((2, 2)),\n",
" layers.Conv2D(64, (3, 3), activation='relu'),\n",
" layers.MaxPooling2D((2, 2)),\n",
" layers.Flatten(),\n",
" layers.Dense(128, activation='relu'),\n",
" layers.Dense(10, activation='softmax')\n",
"])\n",
"\n",
"cnn_model.compile(\n",
" optimizer='adam',\n",
" loss='sparse_categorical_crossentropy',\n",
" metrics=['accuracy']\n",
")\n",
"\n",
"cnn_model.fit(X_train_cnn, y_train, epochs=3, validation_split=0.2)\n",
"```\n",
" "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"--- \n",
"### Deep Learning Unlocked! \n",
"You've now mastered TensorFlow/Keras, the most popular deep learning framework.\n",
"Next: **Model Deployment with Streamlit**."
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.12.7"
}
},
"nbformat": 4,
"nbformat_minor": 4
}