{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "uzjkRr7NmPSx"
      },
      "source": [
        "<p><img alt=\"SOS logo\" height=\"45px\" src=\"https://indico.in2p3.fr/event/37891/logo-2009395760.png\" align=\"left\" hspace=\"10px\" vspace=\"0px\"></p> <h1>SOS 2026</h1>\n",
        "\n",
        "\n",
        "<h1>Hands-on: deep learning - advanced</h1>\n",
        "\n",
        "Author Florian Ruppin"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "GDTWN-VsmPSy"
      },
      "source": [
        "## **Goal of the session**\n",
        "\n",
        "This notebook is a follow-up for students who are already comfortable with the content of the introductory course and the first hands-on notebook (multilayer perceptron coded from scratch + a first TensorFlow/Keras model).\n",
        "\n",
        "Here you will explore, **using Keras**, four tools that are routinely used to build and improve modern neural networks:\n",
        "\n",
        "1. **Regularization** - fighting overfitting (dropout, weight decay, batch normalization)\n",
        "2. **Skip connections** - the Keras *functional API* and residual blocks\n",
        "3. **Convolutional neural networks (CNN)** - the standard architecture for images\n",
        "4. **Autoencoders** - *bonus*, encoding/decoding images (image deblurring)\n",
        "\n",
        "Each section contains an **Example** cell (already written - read it and run it) and a **Your turn** cell (a scaffold for you to complete).\n",
        "\n",
        "> On Google Colab, switch to a GPU runtime for faster training: **Runtime --> Change runtime type --> Hardware accelerator --> GPU**."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "bl_UHdO9mPSy"
      },
      "source": [
        "---\n",
        "\n",
        "## 0. Setup\n",
        "\n",
        "The cell below imports everything we need, loads the MNIST database once, and prepares two versions of the data:\n",
        "\n",
        "- a **flat** version (vectors of 784 values) for the dense networks of sections 1-2;\n",
        "- an **image** version (28-28-1) for the CNN and the autoencoder.\n",
        "\n",
        "It also builds a small training subset so that the overfitting demonstrations train in a few seconds, and defines a helper function `plot_history` to visualize the training curves."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 1,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "_8CwrW_vmPSy",
        "outputId": "5dab6197-bc08-4b96-ff41-3ab26e873b97"
      },
      "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[1m2s\u001b[0m 0us/step\n",
            "Flat shapes : (60000, 784) (10000, 784)\n",
            "Image shapes: (60000, 28, 28, 1) (10000, 28, 28, 1)\n",
            "Small subset: (2000, 784)\n"
          ]
        }
      ],
      "source": [
        "import numpy as np\n",
        "import matplotlib.pyplot as plt\n",
        "from tensorflow import keras\n",
        "from keras.datasets import mnist\n",
        "from keras.models import Sequential, Model\n",
        "from keras.layers import (Input, Dense, Dropout, BatchNormalization,\n",
        "                          Activation, Add, Conv2D, MaxPooling2D,\n",
        "                          Flatten, Conv2DTranspose)\n",
        "from keras.utils import to_categorical\n",
        "from keras import regularizers\n",
        "\n",
        "# ---- Load MNIST once ----\n",
        "(x_train_img, y_train), (x_test_img, y_test) = mnist.load_data()\n",
        "\n",
        "# Normalize to [0, 1]\n",
        "x_train_img = x_train_img.astype('float32') / 255.0\n",
        "x_test_img  = x_test_img.astype('float32') / 255.0\n",
        "\n",
        "# Flat version (for dense networks): shape (n, 784)\n",
        "x_train = x_train_img.reshape(x_train_img.shape[0], -1)\n",
        "x_test  = x_test_img.reshape(x_test_img.shape[0], -1)\n",
        "\n",
        "# Image version with explicit channel (for CNN / autoencoder): shape (n, 28, 28, 1)\n",
        "x_train_cnn = np.expand_dims(x_train_img, -1)\n",
        "x_test_cnn  = np.expand_dims(x_test_img, -1)\n",
        "\n",
        "# One-hot encoded labels\n",
        "y_train_oh = to_categorical(y_train, 10)\n",
        "y_test_oh  = to_categorical(y_test, 10)\n",
        "\n",
        "# Small subset to make overfitting clearly visible and training fast\n",
        "N_small = 2000\n",
        "x_small, y_small = x_train[:N_small], y_train_oh[:N_small]\n",
        "\n",
        "print('Flat shapes :', x_train.shape, x_test.shape)\n",
        "print('Image shapes:', x_train_cnn.shape, x_test_cnn.shape)\n",
        "print('Small subset:', x_small.shape)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 2,
      "metadata": {
        "id": "kGuCnO1QmPS0"
      },
      "outputs": [],
      "source": [
        "def plot_history(history, title=''):\n",
        "    \"\"\"Plot training/validation loss and accuracy from a Keras History object.\n",
        "\n",
        "    Parameters\n",
        "    ----------\n",
        "    history : keras.callbacks.History\n",
        "        The object returned by model.fit(...).\n",
        "    title : str\n",
        "        Optional title prefix for the figure.\n",
        "    \"\"\"\n",
        "    h = history.history\n",
        "    fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(11, 4))\n",
        "    ax1.plot(h['loss'], label='training')\n",
        "    ax1.plot(h['val_loss'], label='validation')\n",
        "    ax1.set_xlabel('epoch'); ax1.set_ylabel('loss'); ax1.legend()\n",
        "    ax1.set_title(f'{title} loss')\n",
        "    ax2.plot(h['accuracy'], label='training')\n",
        "    ax2.plot(h['val_accuracy'], label='validation')\n",
        "    ax2.set_xlabel('epoch'); ax2.set_ylabel('accuracy'); ax2.legend()\n",
        "    ax2.set_title(f'{title} accuracy')\n",
        "    plt.tight_layout(); plt.show()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "vZcjXe-JmPS0"
      },
      "source": [
        "---\n",
        "\n",
        "## 1. A baseline that overfits\n",
        "\n",
        "Before fixing overfitting, let's *produce* it. We train a deliberately oversized dense network on the small 2000-image subset for many epochs. Because the model has far more free parameters than it needs and sees very little data, it will memorize the training set: the **training** accuracy will keep climbing while the **validation** loss eventually *rises* again - the signature of overfitting.\n",
        "\n",
        "**Example (provided - just run it).**"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 3,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 374
        },
        "id": "NjgOk8BomPS0",
        "outputId": "15ed41fe-d681-48c8-a7f4-255643ef85a6"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1100x400 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Final validation accuracy: 0.9210000038146973\n"
          ]
        }
      ],
      "source": [
        "def build_baseline():\n",
        "    \"\"\"A plain (unregularized) dense classifier for flat MNIST.\"\"\"\n",
        "    model = Sequential([\n",
        "        Input(shape=(784,)),\n",
        "        Dense(256, activation='relu'),\n",
        "        Dense(256, activation='relu'),\n",
        "        Dense(10,  activation='softmax'),\n",
        "    ])\n",
        "    model.compile(optimizer=keras.optimizers.Adam(1e-3),\n",
        "                  loss='categorical_crossentropy', metrics=['accuracy'])\n",
        "    return model\n",
        "\n",
        "baseline = build_baseline()\n",
        "hist_baseline = baseline.fit(x_small, y_small,\n",
        "                             validation_data=(x_test, y_test_oh),\n",
        "                             batch_size=64, epochs=60, verbose=0)\n",
        "plot_history(hist_baseline, title='Baseline (no regularization):')\n",
        "print('Final validation accuracy:', hist_baseline.history['val_accuracy'][-1])"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "2jfwmB2TmPS1"
      },
      "source": [
        "**What to observe.** The training loss keeps decreasing toward 0 while the validation loss flattens and then turns upward. The gap between the training and validation curves is the overfitting we now want to reduce."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "scQYkZ0JmPS1"
      },
      "source": [
        "---\n",
        "\n",
        "## 2. Regularization\n",
        "\n",
        "Three widely used tools reduce overfitting and help the network generalize so that its performance on the test sample matches the training sample:\n",
        "\n",
        "- **Dropout** - randomly switches off a fraction of neurons at each training step ([explanation](https://towardsdatascience.com/dropout-in-neural-networks-47a162d621d9))\n",
        "- **L1 / L2 regularization** (a.k.a. *weight decay*) - penalizes large weights ([explanation](https://medium.com/@alejandro.itoaramendia/l1-and-l2-regularization-part-1-a-complete-guide-51cf45bb4ade))\n",
        "- **Batch normalization** - normalizes the activations inside the network ([explanation](https://medium.com/@ghoshanurag66/batch-normalization-math-and-implementation-fe06293f7443))\n",
        "\n",
        "### 2.1 Example: dropout\n",
        "\n",
        "**Example (provided - just run it).** Same architecture as the baseline, but with a `Dropout` layer after each hidden layer."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 4,
      "metadata": {
        "id": "U_ati7-lmPS2",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 374
        },
        "outputId": "9f37fd59-d182-46df-dec6-d2e5a6fd1562"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1100x400 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Final validation accuracy: 0.9196000099182129\n"
          ]
        }
      ],
      "source": [
        "def build_dropout():\n",
        "    \"\"\"Dense classifier with dropout after each hidden layer.\"\"\"\n",
        "    model = Sequential([\n",
        "        Input(shape=(784,)),\n",
        "        Dense(256, activation='relu'),\n",
        "        Dropout(0.4),\n",
        "        Dense(256, activation='relu'),\n",
        "        Dropout(0.4),\n",
        "        Dense(10,  activation='softmax'),\n",
        "    ])\n",
        "    model.compile(optimizer=keras.optimizers.Adam(1e-3),\n",
        "                  loss='categorical_crossentropy', metrics=['accuracy'])\n",
        "    return model\n",
        "\n",
        "dropout_model = build_dropout()\n",
        "hist_dropout = dropout_model.fit(x_small, y_small,\n",
        "                                 validation_data=(x_test, y_test_oh),\n",
        "                                 batch_size=64, epochs=60, verbose=0)\n",
        "plot_history(hist_dropout, title='With dropout:')\n",
        "print('Final validation accuracy:', hist_dropout.history['val_accuracy'][-1])"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Uw1nbB5kmPS2"
      },
      "source": [
        "**What to observe.** The training and validation curves stay much closer together, and the validation loss no longer turns sharply upward.\n",
        "\n",
        "### 2.2 Your turn: weight decay + batch normalization\n",
        "\n",
        "**Your turn.** Complete `build_regularized()` below so that it combines **two** new ingredients on top of the baseline:\n",
        "\n",
        "- **L2 weight decay** on each hidden `Dense` layer, via the keyword `kernel_regularizer=regularizers.l2(1e-4)`;\n",
        "- a **`BatchNormalization()`** layer inserted *between* the dense layer and its ReLU activation (so use a separate `Activation('relu')` layer instead of `activation='relu'`).\n",
        "\n",
        "Then train it on the same subset and compare the curves with the baseline and the dropout model."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "s82Dc5TOmPS2",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 374
        },
        "outputId": "aa7d4a71-ef62-435d-c607-ceda6631b28a"
      },
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1100x400 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Final validation accuracy: 0.9146999716758728\n"
          ]
        }
      ],
      "source": [
        "def build_regularized():\n",
        "    \"\"\"Dense classifier with L2 weight decay + batch normalization.\n",
        "\n",
        "    Returns\n",
        "    -------\n",
        "    keras.Model\n",
        "        A compiled model ready to be trained.\n",
        "    \"\"\"\n",
        "    model = Sequential()\n",
        "    model.add(Input(shape=(784,)))\n",
        "    # For each hidden layer: Dense (no activation) -> BatchNorm -> ReLU.\n",
        "    # Putting the activation AFTER batch normalization is the usual ordering.\n",
        "    for _ in range(2):\n",
        "        model.add(Dense(256, kernel_regularizer=regularizers.l2(1e-4)))\n",
        "        model.add(BatchNormalization())\n",
        "        model.add(Activation('relu'))\n",
        "    model.add(Dense(10, activation='softmax'))\n",
        "    model.compile(optimizer=keras.optimizers.Adam(1e-3),\n",
        "                  loss='categorical_crossentropy', metrics=['accuracy'])\n",
        "    return model\n",
        "\n",
        "reg_model = build_regularized()\n",
        "hist_reg = reg_model.fit(x_small, y_small,\n",
        "                         validation_data=(x_test, y_test_oh),\n",
        "                         batch_size=64, epochs=60, verbose=0)\n",
        "plot_history(hist_reg, title='L2 + batch norm:')\n",
        "print('Final validation accuracy:', hist_reg.history['val_accuracy'][-1])"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "_n3beW3omPS2"
      },
      "source": [
        "---\n",
        "\n",
        "## 3. Skip connections (Keras functional API)\n",
        "\n",
        "**Skip connections** (or *residual* connections) add the input of a block directly to its output: `output = activation(x + block(x))`. They were introduced to mitigate the *vanishing gradient* problem and allow much deeper networks to train.\n",
        "\n",
        "- Theory: [skip connections](https://theaisummer.com/skip-connections/)\n",
        "- Practice: [Keras functional API guide](https://keras.io/guides/functional_api/)\n",
        "\n",
        "Skip connections cannot be expressed with the simple `Sequential` API because the data flow is no longer a straight line. We use the **functional API**, where each layer is *called* on a tensor and we explicitly wire the graph, then wrap it with `Model(inputs, outputs)`.\n",
        "\n",
        "### 3.1 Example: one residual block\n",
        "\n",
        "**Example (provided - just run it).** Note how `Add()([x, h])` merges the skip path `x` with the block output `h` (both must have the same shape: here 128 units)."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 6,
      "metadata": {
        "id": "VsHd26iimPS3",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 823
        },
        "outputId": "598b2087-011e-4980-9dac-3f03367a5949"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1mModel: \"functional_9\"\u001b[0m\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"functional_9\"</span>\n",
              "</pre>\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┃\u001b[1m \u001b[0m\u001b[1mConnected to     \u001b[0m\u001b[1m \u001b[0m┃\n",
              "┡━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━┩\n",
              "│ input_layer_3       │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m784\u001b[0m)       │          \u001b[38;5;34m0\u001b[0m │ -                 │\n",
              "│ (\u001b[38;5;33mInputLayer\u001b[0m)        │                   │            │                   │\n",
              "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
              "│ dense_9 (\u001b[38;5;33mDense\u001b[0m)     │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)       │    \u001b[38;5;34m100,480\u001b[0m │ input_layer_3[\u001b[38;5;34m0\u001b[0m]… │\n",
              "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
              "│ dense_10 (\u001b[38;5;33mDense\u001b[0m)    │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)       │     \u001b[38;5;34m16,512\u001b[0m │ dense_9[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m]     │\n",
              "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
              "│ dense_11 (\u001b[38;5;33mDense\u001b[0m)    │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)       │     \u001b[38;5;34m16,512\u001b[0m │ dense_10[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m]    │\n",
              "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
              "│ add (\u001b[38;5;33mAdd\u001b[0m)           │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)       │          \u001b[38;5;34m0\u001b[0m │ dense_9[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m],    │\n",
              "│                     │                   │            │ dense_11[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m]    │\n",
              "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
              "│ activation_2        │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)       │          \u001b[38;5;34m0\u001b[0m │ add[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m]         │\n",
              "│ (\u001b[38;5;33mActivation\u001b[0m)        │                   │            │                   │\n",
              "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
              "│ dense_12 (\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 │ activation_2[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m…\u001b[0m │\n",
              "└─────────────────────┴───────────────────┴────────────┴───────────────────┘\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━┓\n",
              "┃<span style=\"font-weight: bold\"> Layer (type)        </span>┃<span style=\"font-weight: bold\"> Output Shape      </span>┃<span style=\"font-weight: bold\">    Param # </span>┃<span style=\"font-weight: bold\"> Connected to      </span>┃\n",
              "┡━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━┩\n",
              "│ input_layer_3       │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">784</span>)       │          <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │ -                 │\n",
              "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">InputLayer</span>)        │                   │            │                   │\n",
              "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
              "│ dense_9 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)     │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)       │    <span style=\"color: #00af00; text-decoration-color: #00af00\">100,480</span> │ input_layer_3[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>]… │\n",
              "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
              "│ dense_10 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)    │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)       │     <span style=\"color: #00af00; text-decoration-color: #00af00\">16,512</span> │ dense_9[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>]     │\n",
              "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
              "│ dense_11 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)    │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)       │     <span style=\"color: #00af00; text-decoration-color: #00af00\">16,512</span> │ dense_10[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>]    │\n",
              "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
              "│ add (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Add</span>)           │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)       │          <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │ dense_9[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>],    │\n",
              "│                     │                   │            │ dense_11[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>]    │\n",
              "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
              "│ activation_2        │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)       │          <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │ add[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>]         │\n",
              "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Activation</span>)        │                   │            │                   │\n",
              "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
              "│ dense_12 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)    │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">10</span>)        │      <span style=\"color: #00af00; text-decoration-color: #00af00\">1,290</span> │ activation_2[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">…</span> │\n",
              "└─────────────────────┴───────────────────┴────────────┴───────────────────┘\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m134,794\u001b[0m (526.54 KB)\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">134,794</span> (526.54 KB)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m134,794\u001b[0m (526.54 KB)\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">134,794</span> (526.54 KB)\n",
              "</pre>\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": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (0.00 B)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1100x400 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "def residual_block(x, units):\n",
        "    \"\"\"A simple residual block: two Dense layers + a skip connection.\n",
        "\n",
        "    Parameters\n",
        "    ----------\n",
        "    x : tensor\n",
        "        Input tensor of shape (..., units).\n",
        "    units : int\n",
        "        Width of the block (must match the last dimension of x).\n",
        "\n",
        "    Returns\n",
        "    -------\n",
        "    tensor\n",
        "        Output tensor of shape (..., units).\n",
        "    \"\"\"\n",
        "    h = Dense(units, activation='relu')(x)\n",
        "    h = Dense(units)(h)            # no activation before the merge\n",
        "    out = Add()([x, h])            # skip connection: x + block(x)\n",
        "    out = Activation('relu')(out)\n",
        "    return out\n",
        "\n",
        "inputs = Input(shape=(784,))\n",
        "x = Dense(128, activation='relu')(inputs)   # project to 128 units\n",
        "x = residual_block(x, 128)                  # one residual block\n",
        "outputs = Dense(10, activation='softmax')(x)\n",
        "\n",
        "resnet1 = Model(inputs, outputs)\n",
        "resnet1.compile(optimizer=keras.optimizers.Adam(1e-3),\n",
        "                loss='categorical_crossentropy', metrics=['accuracy'])\n",
        "resnet1.summary()\n",
        "\n",
        "hist_res1 = resnet1.fit(x_small, y_small,\n",
        "                        validation_data=(x_test, y_test_oh),\n",
        "                        batch_size=64, epochs=30, verbose=0)\n",
        "plot_history(hist_res1, title='1 residual block:')"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "EYW11jpEmPS3"
      },
      "source": [
        "### 3.2 Your turn: stack a second residual block\n",
        "\n",
        "**Your turn.** Using the `residual_block` function above, build a deeper network with **two** residual blocks stacked one after the other (still 128 units each), then train it.\n",
        "\n",
        "- Start from `Input(shape=(784,))`.\n",
        "- Project to 128 units with a `Dense(128, activation='relu')` layer.\n",
        "- Apply `residual_block(..., 128)` **twice**.\n",
        "- Finish with `Dense(10, activation='softmax')` and wrap everything in a `Model`."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Rs6oXlN5mPS3",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 917
        },
        "outputId": "9a24e6e8-e0b6-4b38-a5d6-394f2a4c2a7e"
      },
      "execution_count": 7,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1mModel: \"functional_10\"\u001b[0m\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"functional_10\"</span>\n",
              "</pre>\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┃\u001b[1m \u001b[0m\u001b[1mConnected to     \u001b[0m\u001b[1m \u001b[0m┃\n",
              "┡━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━┩\n",
              "│ input_layer_4       │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m784\u001b[0m)       │          \u001b[38;5;34m0\u001b[0m │ -                 │\n",
              "│ (\u001b[38;5;33mInputLayer\u001b[0m)        │                   │            │                   │\n",
              "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
              "│ dense_13 (\u001b[38;5;33mDense\u001b[0m)    │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)       │    \u001b[38;5;34m100,480\u001b[0m │ input_layer_4[\u001b[38;5;34m0\u001b[0m]… │\n",
              "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
              "│ dense_14 (\u001b[38;5;33mDense\u001b[0m)    │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)       │     \u001b[38;5;34m16,512\u001b[0m │ dense_13[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m]    │\n",
              "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
              "│ dense_15 (\u001b[38;5;33mDense\u001b[0m)    │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)       │     \u001b[38;5;34m16,512\u001b[0m │ dense_14[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m]    │\n",
              "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
              "│ add_1 (\u001b[38;5;33mAdd\u001b[0m)         │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)       │          \u001b[38;5;34m0\u001b[0m │ dense_13[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m],   │\n",
              "│                     │                   │            │ dense_15[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m]    │\n",
              "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
              "│ activation_3        │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)       │          \u001b[38;5;34m0\u001b[0m │ add_1[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m]       │\n",
              "│ (\u001b[38;5;33mActivation\u001b[0m)        │                   │            │                   │\n",
              "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
              "│ dense_16 (\u001b[38;5;33mDense\u001b[0m)    │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)       │     \u001b[38;5;34m16,512\u001b[0m │ activation_3[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m…\u001b[0m │\n",
              "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
              "│ dense_17 (\u001b[38;5;33mDense\u001b[0m)    │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)       │     \u001b[38;5;34m16,512\u001b[0m │ dense_16[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m]    │\n",
              "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
              "│ add_2 (\u001b[38;5;33mAdd\u001b[0m)         │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)       │          \u001b[38;5;34m0\u001b[0m │ activation_3[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m…\u001b[0m │\n",
              "│                     │                   │            │ dense_17[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m]    │\n",
              "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
              "│ activation_4        │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)       │          \u001b[38;5;34m0\u001b[0m │ add_2[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m]       │\n",
              "│ (\u001b[38;5;33mActivation\u001b[0m)        │                   │            │                   │\n",
              "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
              "│ dense_18 (\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 │ activation_4[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m…\u001b[0m │\n",
              "└─────────────────────┴───────────────────┴────────────┴───────────────────┘\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━┓\n",
              "┃<span style=\"font-weight: bold\"> Layer (type)        </span>┃<span style=\"font-weight: bold\"> Output Shape      </span>┃<span style=\"font-weight: bold\">    Param # </span>┃<span style=\"font-weight: bold\"> Connected to      </span>┃\n",
              "┡━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━┩\n",
              "│ input_layer_4       │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">784</span>)       │          <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │ -                 │\n",
              "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">InputLayer</span>)        │                   │            │                   │\n",
              "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
              "│ dense_13 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)    │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)       │    <span style=\"color: #00af00; text-decoration-color: #00af00\">100,480</span> │ input_layer_4[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>]… │\n",
              "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
              "│ dense_14 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)    │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)       │     <span style=\"color: #00af00; text-decoration-color: #00af00\">16,512</span> │ dense_13[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>]    │\n",
              "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
              "│ dense_15 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)    │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)       │     <span style=\"color: #00af00; text-decoration-color: #00af00\">16,512</span> │ dense_14[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>]    │\n",
              "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
              "│ add_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Add</span>)         │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)       │          <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │ dense_13[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>],   │\n",
              "│                     │                   │            │ dense_15[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>]    │\n",
              "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
              "│ activation_3        │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)       │          <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │ add_1[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>]       │\n",
              "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Activation</span>)        │                   │            │                   │\n",
              "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
              "│ dense_16 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)    │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)       │     <span style=\"color: #00af00; text-decoration-color: #00af00\">16,512</span> │ activation_3[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">…</span> │\n",
              "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
              "│ dense_17 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)    │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)       │     <span style=\"color: #00af00; text-decoration-color: #00af00\">16,512</span> │ dense_16[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>]    │\n",
              "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
              "│ add_2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Add</span>)         │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)       │          <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │ activation_3[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">…</span> │\n",
              "│                     │                   │            │ dense_17[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>]    │\n",
              "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
              "│ activation_4        │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)       │          <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │ add_2[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>]       │\n",
              "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Activation</span>)        │                   │            │                   │\n",
              "├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
              "│ dense_18 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)    │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">10</span>)        │      <span style=\"color: #00af00; text-decoration-color: #00af00\">1,290</span> │ activation_4[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">…</span> │\n",
              "└─────────────────────┴───────────────────┴────────────┴───────────────────┘\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m167,818\u001b[0m (655.54 KB)\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">167,818</span> (655.54 KB)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m167,818\u001b[0m (655.54 KB)\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">167,818</span> (655.54 KB)\n",
              "</pre>\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": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (0.00 B)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1100x400 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "# Two residual blocks stacked one after the other (128 units each).\n",
        "inputs  = Input(shape=(784,))\n",
        "x       = Dense(128, activation='relu')(inputs)   # project to 128 units\n",
        "x       = residual_block(x, 128)                   # first residual block\n",
        "x       = residual_block(x, 128)                   # second residual block\n",
        "outputs = Dense(10, activation='softmax')(x)\n",
        "\n",
        "resnet2 = Model(inputs, outputs)\n",
        "resnet2.compile(optimizer=keras.optimizers.Adam(1e-3),\n",
        "                loss='categorical_crossentropy', metrics=['accuracy'])\n",
        "\n",
        "resnet2.summary()\n",
        "hist_res2 = resnet2.fit(x_small, y_small,\n",
        "                        validation_data=(x_test, y_test_oh),\n",
        "                        batch_size=64, epochs=30, verbose=0)\n",
        "plot_history(hist_res2, title='2 residual blocks:')"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "0tgS-drSmPS3"
      },
      "source": [
        "---\n",
        "\n",
        "## 4. Convolutional neural network (CNN)\n",
        "\n",
        "CNNs are the standard architecture for image recognition. Instead of flattening the image, they slide small learnable **filters** (kernels) across it to extract local features, preserving the 2-D spatial structure.\n",
        "\n",
        "<p style=\"text-align:center\">\n",
        "    <img alt=\"ConvNet\" width=\"750px\" src=\"https://editor.analyticsvidhya.com/uploads/94787Convolutional-Neural-Network.jpeg\" hspace=\"10px\" vspace=\"0px\">\n",
        "</p>\n",
        "\n",
        "A convolution layer runs a kernel (an N&times;N matrix of weights, *learned* during training) over the image to produce a new feature map that is passed to the next layer.\n",
        "\n",
        "### 4.1 Example: a small CNN on MNIST\n",
        "\n",
        "**Example (provided &mdash; just run it).** We train on a subset for 3 epochs to keep it fast; even so, the test accuracy is typically higher than the dense network from the first notebook. Use a GPU runtime if it feels slow."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "ZY219Qx_mPS3"
      },
      "outputs": [],
      "source": [
        "# Use a subset so the CNN trains quickly during the session\n",
        "N_cnn = 12000\n",
        "xc_train, yc_train = x_train_cnn[:N_cnn], y_train_oh[:N_cnn]\n",
        "\n",
        "cnn = Sequential([\n",
        "    Input(shape=(28, 28, 1)),\n",
        "    Conv2D(32, kernel_size=(3, 3), activation='relu'),\n",
        "    MaxPooling2D(pool_size=(2, 2)),\n",
        "    Conv2D(64, kernel_size=(3, 3), activation='relu'),\n",
        "    MaxPooling2D(pool_size=(2, 2)),\n",
        "    Flatten(),\n",
        "    Dropout(0.5),\n",
        "    Dense(10, activation='softmax'),\n",
        "])\n",
        "cnn.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])\n",
        "cnn.summary()\n",
        "\n",
        "cnn.fit(xc_train, yc_train, batch_size=128, epochs=3, validation_split=0.1)\n",
        "score = cnn.evaluate(x_test_cnn, y_test_oh, verbose=0)\n",
        "print(f'Test loss: {score[0]:.4f}  |  test accuracy: {score[1]:.4f}')"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "xSd-DzbGmPS4"
      },
      "source": [
        "### 4.2 Your turn: deepen the CNN\n",
        "\n",
        "**Your turn.** Build a second CNN (`cnn2`) with a bit more capacity and compare its test accuracy with the one above. For example:\n",
        "\n",
        "- add a **third** `Conv2D` block (e.g. 128 filters) &mdash; *or* increase the number of filters in the existing layers;\n",
        "- optionally insert a `Dense(64, activation='relu')` layer before the output.\n",
        "\n",
        "Keep the same input shape `(28, 28, 1)` and the softmax output of 10 units. Watch out: every `MaxPooling2D` halves the spatial size, so you can only pool while the feature map stays larger than the kernel."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "5EE9y0YVmPS4"
      },
      "execution_count": null,
      "outputs": [],
      "source": [
        "# Deeper CNN: a third convolutional block + a dense layer before the output.\n",
        "# Note: each Conv2D (valid padding) shrinks the map by 2 pixels, each MaxPooling\n",
        "# halves it -> 28 -> 26 -> 13 -> 11 -> 5 -> 3, which stays positive.\n",
        "cnn2 = Sequential([\n",
        "    Input(shape=(28, 28, 1)),\n",
        "    Conv2D(32, kernel_size=(3, 3), activation='relu'),\n",
        "    MaxPooling2D(pool_size=(2, 2)),\n",
        "    Conv2D(64, kernel_size=(3, 3), activation='relu'),\n",
        "    MaxPooling2D(pool_size=(2, 2)),\n",
        "    Conv2D(128, kernel_size=(3, 3), activation='relu'),\n",
        "    Flatten(),\n",
        "    Dense(64, activation='relu'),\n",
        "    Dropout(0.5),\n",
        "    Dense(10, activation='softmax'),\n",
        "])\n",
        "cnn2.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])\n",
        "cnn2.summary()\n",
        "\n",
        "cnn2.fit(xc_train, yc_train, batch_size=128, epochs=3, validation_split=0.1)\n",
        "\n",
        "score2 = cnn2.evaluate(x_test_cnn, y_test_oh, verbose=0)\n",
        "print(f'cnn2 test accuracy: {score2[1]:.4f}  (baseline CNN: {score[1]:.4f})')"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "NfMxtI8NmPS4"
      },
      "source": [
        "---\n",
        "\n",
        "## 5. Bonus &mdash; Autoencoder for image deblurring\n",
        "\n",
        "> *This section is a bonus and is **not** part of the 30-minute budget &mdash; tackle it if you finish early.*\n",
        "\n",
        "An **autoencoder** compresses (encodes) an input into a lower-dimensional representation and then reconstructs (decodes) a target image from it. A classic use case is *denoising*; here we will instead **deblur** images.\n",
        "\n",
        "<p style=\"text-align:center\">\n",
        "    <img alt=\"Autoencoder\" width=\"750px\" src=\"https://www.researchgate.net/profile/Xifeng-Guo/publication/320658590/figure/fig1/AS:614154637418504@1523437284408/The-structure-of-proposed-Convolutional-AutoEncoders-CAE-for-MNIST-In-the-middle-there.png\" hspace=\"10px\" vspace=\"0px\">\n",
        "</p>\n",
        "\n",
        "We follow the structure of the official [Keras denoising autoencoder example](https://keras.io/examples/vision/autoencoder/), but replace the *noise* corruption with a *blur* corruption: each (N&times;N) block of pixels is replaced by its mean value (pixelation).\n",
        "\n",
        "### 5.1 Example: the blur corruption\n",
        "\n",
        "**Example (provided &mdash; just run it).**"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "SMKzZQ3_mPS4"
      },
      "outputs": [],
      "source": [
        "def add_blur(images, block=4):\n",
        "    \"\"\"Block-average blur: replace each (block x block) patch by its mean value.\n",
        "\n",
        "    Parameters\n",
        "    ----------\n",
        "    images : ndarray, shape (n, H, W, 1)\n",
        "        Input images with H and W divisible by `block` (28 is divisible by 4).\n",
        "    block : int\n",
        "        Side length of the averaging block.\n",
        "\n",
        "    Returns\n",
        "    -------\n",
        "    ndarray, same shape as `images`\n",
        "        The blurred images.\n",
        "    \"\"\"\n",
        "    imgs = np.asarray(images, dtype='float32')\n",
        "    n, H, W, C = imgs.shape\n",
        "    r = imgs.reshape(n, H // block, block, W // block, block, C)\n",
        "    m = r.mean(axis=(2, 4), keepdims=True)\n",
        "    return np.broadcast_to(m, r.shape).reshape(n, H, W, C).copy()\n",
        "\n",
        "x_train_blur = add_blur(x_train_cnn, block=4)\n",
        "x_test_blur  = add_blur(x_test_cnn,  block=4)\n",
        "\n",
        "# Visual check: top row = blurred (input), bottom row = sharp (target)\n",
        "fig, axes = plt.subplots(2, 6, figsize=(10, 3.5))\n",
        "for k in range(6):\n",
        "    axes[0, k].imshow(x_test_blur[k, :, :, 0], cmap='gray'); axes[0, k].axis('off')\n",
        "    axes[1, k].imshow(x_test_cnn[k, :, :, 0],  cmap='gray'); axes[1, k].axis('off')\n",
        "axes[0, 0].set_title('blurred', loc='left')\n",
        "axes[1, 0].set_title('sharp',   loc='left')\n",
        "plt.tight_layout(); plt.show()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "yTNONPk2mPS4"
      },
      "source": [
        "### 5.2 Your turn: build and train the deblurring autoencoder\n",
        "\n",
        "**Your turn.** Build a small convolutional autoencoder that maps a **blurred** image to its **sharp** version.\n",
        "\n",
        "- Input shape `(28, 28, 1)`.\n",
        "- **Encoder**: a couple of `Conv2D(..., activation='relu', padding='same')` layers, each followed by `MaxPooling2D((2, 2), padding='same')` to downsample.\n",
        "- **Decoder**: `Conv2DTranspose(..., strides=2, activation='relu', padding='same')` layers to upsample back to 28&times;28, then a final `Conv2D(1, (3, 3), activation='sigmoid', padding='same')` so the output pixels lie in [0, 1].\n",
        "- Compile with `optimizer='adam'` and `loss='binary_crossentropy'` (or `'mse'`).\n",
        "- Train with **input** `x_train_blur` and **target** `x_train_cnn` (the sharp images), using `validation_data=(x_test_blur, x_test_cnn)`. A few epochs are enough to see an effect."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "hAxlvHlBmPS4"
      },
      "execution_count": null,
      "outputs": [],
      "source": [
        "# Convolutional autoencoder: blurred image -> sharp image.\n",
        "inp = Input(shape=(28, 28, 1))\n",
        "\n",
        "# Encoder: two conv + pooling stages (28 -> 14 -> 7)\n",
        "x = Conv2D(32, (3, 3), activation='relu', padding='same')(inp)\n",
        "x = MaxPooling2D((2, 2), padding='same')(x)\n",
        "x = Conv2D(32, (3, 3), activation='relu', padding='same')(x)\n",
        "encoded = MaxPooling2D((2, 2), padding='same')(x)\n",
        "\n",
        "# Decoder: two transposed-conv stages upsample back (7 -> 14 -> 28)\n",
        "x = Conv2DTranspose(32, (3, 3), strides=2, activation='relu', padding='same')(encoded)\n",
        "x = Conv2DTranspose(32, (3, 3), strides=2, activation='relu', padding='same')(x)\n",
        "decoded = Conv2D(1, (3, 3), activation='sigmoid', padding='same')(x)\n",
        "\n",
        "autoencoder = Model(inp, decoded)\n",
        "autoencoder.compile(optimizer='adam', loss='binary_crossentropy')\n",
        "autoencoder.summary()\n",
        "\n",
        "# Train on a subset to keep it fast: input = blurred, target = sharp\n",
        "autoencoder.fit(x_train_blur[:12000], x_train_cnn[:12000],\n",
        "                validation_data=(x_test_blur, x_test_cnn),\n",
        "                batch_size=128, epochs=5)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "1CU_K3IjmPS5"
      },
      "source": [
        "**Your turn.** Once trained, run the autoencoder on a few blurred test images and display the three rows side by side: **blurred input**, **autoencoder output**, **sharp target**. Reuse the plotting pattern from the Example cell in 5.1."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "B-PEb-WFmPS5"
      },
      "execution_count": null,
      "outputs": [],
      "source": [
        "# Deblur a few test images and compare input / output / target.\n",
        "decoded_imgs = autoencoder.predict(x_test_blur[:6])\n",
        "\n",
        "fig, axes = plt.subplots(3, 6, figsize=(10, 5))\n",
        "for k in range(6):\n",
        "    axes[0, k].imshow(x_test_blur[k, :, :, 0],   cmap='gray'); axes[0, k].axis('off')\n",
        "    axes[1, k].imshow(decoded_imgs[k, :, :, 0],  cmap='gray'); axes[1, k].axis('off')\n",
        "    axes[2, k].imshow(x_test_cnn[k, :, :, 0],    cmap='gray'); axes[2, k].axis('off')\n",
        "axes[0, 0].set_title('blurred (input)',     loc='left')\n",
        "axes[1, 0].set_title('autoencoder output',  loc='left')\n",
        "axes[2, 0].set_title('sharp (target)',      loc='left')\n",
        "plt.tight_layout(); plt.show()"
      ]
    }
  ],
  "metadata": {
    "colab": {
      "provenance": [],
      "toc_visible": true,
      "gpuType": "T4"
    },
    "kernelspec": {
      "display_name": "Python 3",
      "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": "3.9.19"
    },
    "accelerator": "GPU"
  },
  "nbformat": 4,
  "nbformat_minor": 0
}