Created using Colab

cnn.ipynb

@@ -0,0 +1,393 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "view-in-github",
+        "colab_type": "text"
+      },
+      "source": [
+        "<a href=\"https://colab.research.google.com/github/andremicci/Generative_Deep_Learning_2nd_Edition/blob/main/cnn.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [],
+      "metadata": {
+        "id": "Mhp4GfwTjOee"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "!git clone https://github.com/andremicci/Generative_Deep_Learning_2nd_Edition.git"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "KOnmreJbjLIz",
+        "outputId": "a3a49f71-3b29-41cb-fc11-a031442b32a9"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Cloning into 'Generative_Deep_Learning_2nd_Edition'...\n",
+            "remote: Enumerating objects: 653, done.\u001b[K\n",
+            "remote: Counting objects: 100% (195/195), done.\u001b[K\n",
+            "remote: Compressing objects: 100% (70/70), done.\u001b[K\n",
+            "remote: Total 653 (delta 142), reused 125 (delta 125), pack-reused 458 (from 1)\u001b[K\n",
+            "Receiving objects: 100% (653/653), 37.09 MiB | 8.67 MiB/s, done.\n",
+            "Resolving deltas: 100% (377/377), done.\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "TFy-fuvQjJJp"
+      },
+      "source": [
+        "# 🏞 Convolutional Neural Network"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "wEIaaUnijJJr"
+      },
+      "source": [
+        "In this notebook, we'll walk through the steps required to train your own convolutional neural network (CNN) on the CIFAR dataset"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 350
+        },
+        "id": "Ewl7DskxjJJs",
+        "outputId": "72f7b930-03ff-4bab-97c7-8f337c0da519"
+      },
+      "outputs": [
+        {
+          "output_type": "error",
+          "ename": "ModuleNotFoundError",
+          "evalue": "No module named 'notebooks'",
+          "traceback": [
+            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+            "\u001b[0;31mModuleNotFoundError\u001b[0m                       Traceback (most recent call last)",
+            "\u001b[0;32m<ipython-input-2-a230bc8cc151>\u001b[0m in \u001b[0;36m<cell line: 0>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      2\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      3\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mtensorflow\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mkeras\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mlayers\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmodels\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0moptimizers\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mutils\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdatasets\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 4\u001b[0;31m \u001b[0;32mfrom\u001b[0m \u001b[0mnotebooks\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mutils\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mdisplay\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
+            "\u001b[0;31mModuleNotFoundError\u001b[0m: No module named 'notebooks'",
+            "",
+            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0;32m\nNOTE: If your import is failing due to a missing package, you can\nmanually install dependencies using either !pip or !apt.\n\nTo view examples of installing some common dependencies, click the\n\"Open Examples\" button below.\n\u001b[0;31m---------------------------------------------------------------------------\u001b[0m\n"
+          ],
+          "errorDetails": {
+            "actions": [
+              {
+                "action": "open_url",
+                "actionText": "Open Examples",
+                "url": "/notebooks/snippets/importing_libraries.ipynb"
+              }
+            ]
+          }
+        }
+      ],
+      "source": [
+        "import numpy as np\n",
+        "\n",
+        "from tensorflow.keras import layers, models, optimizers, utils, datasets\n",
+        "from notebooks.utils import display"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "tags": [],
+        "id": "5xHzrj8jjJJu"
+      },
+      "source": [
+        "## 0. Parameters <a name=\"parameters\"></a>"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "4dTmq7jjjJJv"
+      },
+      "outputs": [],
+      "source": [
+        "NUM_CLASSES = 10"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "MTLZ1IG6jJJw"
+      },
+      "source": [
+        "## 1. Prepare the Data <a name=\"prepare\"></a>"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "DR22w6jsjJJx"
+      },
+      "outputs": [],
+      "source": [
+        "(x_train, y_train), (x_test, y_test) = datasets.cifar10.load_data()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "gkQBN7pojJJx"
+      },
+      "outputs": [],
+      "source": [
+        "x_train = x_train.astype(\"float32\") / 255.0\n",
+        "x_test = x_test.astype(\"float32\") / 255.0\n",
+        "\n",
+        "y_train = utils.to_categorical(y_train, NUM_CLASSES)\n",
+        "y_test = utils.to_categorical(y_test, NUM_CLASSES)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "p6D1z7qPjJJz"
+      },
+      "outputs": [],
+      "source": [
+        "display(x_train[:10])\n",
+        "print(y_train[:10])"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "uqly1nGYjJJ0"
+      },
+      "source": [
+        "## 2. Build the model <a name=\"build\"></a>"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "rvLwhVf7jJJ1"
+      },
+      "outputs": [],
+      "source": [
+        "input_layer = layers.Input((32, 32, 3))\n",
+        "\n",
+        "x = layers.Conv2D(filters=32, kernel_size=3, strides=1, padding=\"same\")(\n",
+        "    input_layer\n",
+        ")\n",
+        "x = layers.BatchNormalization()(x)\n",
+        "x = layers.LeakyReLU()(x)\n",
+        "\n",
+        "x = layers.Conv2D(filters=32, kernel_size=3, strides=2, padding=\"same\")(x)\n",
+        "x = layers.BatchNormalization()(x)\n",
+        "x = layers.LeakyReLU()(x)\n",
+        "\n",
+        "x = layers.Conv2D(filters=64, kernel_size=3, strides=1, padding=\"same\")(x)\n",
+        "x = layers.BatchNormalization()(x)\n",
+        "x = layers.LeakyReLU()(x)\n",
+        "\n",
+        "x = layers.Conv2D(filters=64, kernel_size=3, strides=2, padding=\"same\")(x)\n",
+        "x = layers.BatchNormalization()(x)\n",
+        "x = layers.LeakyReLU()(x)\n",
+        "\n",
+        "x = layers.Flatten()(x)\n",
+        "\n",
+        "x = layers.Dense(128)(x)\n",
+        "x = layers.BatchNormalization()(x)\n",
+        "x = layers.LeakyReLU()(x)\n",
+        "x = layers.Dropout(rate=0.5)(x)\n",
+        "\n",
+        "x = layers.Dense(NUM_CLASSES)(x)\n",
+        "output_layer = layers.Activation(\"softmax\")(x)\n",
+        "\n",
+        "model = models.Model(input_layer, output_layer)\n",
+        "\n",
+        "model.summary()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "tags": [],
+        "id": "_0JEpfyWjJJ3"
+      },
+      "source": [
+        "## 3. Train the model <a name=\"train\"></a>"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "RQWD-6i6jJJ4"
+      },
+      "outputs": [],
+      "source": [
+        "opt = optimizers.Adam(learning_rate=0.0005)\n",
+        "model.compile(\n",
+        "    loss=\"categorical_crossentropy\", optimizer=opt, metrics=[\"accuracy\"]\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "tags": [],
+        "id": "pajMd0T0jJJ5"
+      },
+      "outputs": [],
+      "source": [
+        "model.fit(\n",
+        "    x_train,\n",
+        "    y_train,\n",
+        "    batch_size=32,\n",
+        "    epochs=10,\n",
+        "    shuffle=True,\n",
+        "    validation_data=(x_test, y_test),\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "tags": [],
+        "id": "M2Jl9j7ljJJ5"
+      },
+      "source": [
+        "## 4. Evaluation <a name=\"evaluate\"></a>"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "t7GXyVvYjJJ6"
+      },
+      "outputs": [],
+      "source": [
+        "model.evaluate(x_test, y_test, batch_size=1000)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "Ttvkm2g_jJJ6"
+      },
+      "outputs": [],
+      "source": [
+        "CLASSES = np.array(\n",
+        "    [\n",
+        "        \"airplane\",\n",
+        "        \"automobile\",\n",
+        "        \"bird\",\n",
+        "        \"cat\",\n",
+        "        \"deer\",\n",
+        "        \"dog\",\n",
+        "        \"frog\",\n",
+        "        \"horse\",\n",
+        "        \"ship\",\n",
+        "        \"truck\",\n",
+        "    ]\n",
+        ")\n",
+        "\n",
+        "preds = model.predict(x_test)\n",
+        "preds_single = CLASSES[np.argmax(preds, axis=-1)]\n",
+        "actual_single = CLASSES[np.argmax(y_test, axis=-1)]"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "5SkFQ0pHjJJ7"
+      },
+      "outputs": [],
+      "source": [
+        "import matplotlib.pyplot as plt\n",
+        "\n",
+        "n_to_show = 10\n",
+        "indices = np.random.choice(range(len(x_test)), n_to_show)\n",
+        "\n",
+        "fig = plt.figure(figsize=(15, 3))\n",
+        "fig.subplots_adjust(hspace=0.4, wspace=0.4)\n",
+        "\n",
+        "for i, idx in enumerate(indices):\n",
+        "    img = x_test[idx]\n",
+        "    ax = fig.add_subplot(1, n_to_show, i + 1)\n",
+        "    ax.axis(\"off\")\n",
+        "    ax.text(\n",
+        "        0.5,\n",
+        "        -0.35,\n",
+        "        \"pred = \" + str(preds_single[idx]),\n",
+        "        fontsize=10,\n",
+        "        ha=\"center\",\n",
+        "        transform=ax.transAxes,\n",
+        "    )\n",
+        "    ax.text(\n",
+        "        0.5,\n",
+        "        -0.7,\n",
+        "        \"act = \" + str(actual_single[idx]),\n",
+        "        fontsize=10,\n",
+        "        ha=\"center\",\n",
+        "        transform=ax.transAxes,\n",
+        "    )\n",
+        "    ax.imshow(img)"
+      ]
+    }
+  ],
+  "metadata": {
+    "kernelspec": {
+      "display_name": "Python 3 (ipykernel)",
+      "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": "3.8.10"
+    },
+    "vscode": {
+      "interpreter": {
+        "hash": "31f2aee4e71d21fbe5cf8b01ff0e069b9275f58929596ceb00d14d90e3e16cd6"
+      }
+    },
+    "colab": {
+      "provenance": [],
+      "include_colab_link": true
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}