{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"<img width=\"800px\" src=\"../fidle/img/header.svg\"></img>\n",
"\n",
"# <!-- TITLE --> [K3GTSRB2] - First convolutions\n",
"<!-- DESC --> Episode 2 : First convolutions and first classification of our traffic signs, using Keras3\n",
"<!-- AUTHOR : Jean-Luc Parouty (CNRS/SIMaP) -->\n",
"\n",
"## Objectives :\n",
" - Recognizing traffic signs \n",
" - Understand the **principles** and **architecture** of a **convolutional neural network** for image classification\n",
" \n",
"The German Traffic Sign Recognition Benchmark (GTSRB) is a dataset with more than 50,000 photos of road signs from about 40 classes. \n",
"The final aim is to recognise them ! \n",
"\n",
"Description is available there : http://benchmark.ini.rub.de/?section=gtsrb&subsection=dataset\n",
"\n",
"\n",
"**IMPORTANT :** To be able to use this notebook and the following, **you must have generated the enhanced datasets** in <dataset_dir>/enhanced via the notebook **[01-Preparation-of-data.ipynb](01-Preparation-of-data.ipynb)** \n",
"\n",
"## What we're going to do :\n",
"\n",
" - Read H5 dataset\n",
" - Build a model\n",
" - Train the model\n",
" - Evaluate the model\n",
"\n",
"## Step 1 - Import and init\n",
"### 1.1 - Python stuff"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"os.environ['KERAS_BACKEND'] = 'torch'\n",
"\n",
"import keras\n",
"\n",
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"import h5py\n",
"import os,time,sys\n",
"\n",
"from importlib import reload\n",
"\n",
"# Init Fidle environment\n",
"import fidle\n",
"\n",
"run_id, run_dir, datasets_dir = fidle.init('K3GTSRB2')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 1.2 - Parameters\n",
"`scale` is the proportion of the dataset that will be used during the training. (1 mean 100%) \n",
"A 20% 24x24 dataset, with 5 epochs and a scale of 1, need **3'30** on a CPU laptop.\\\n",
"`fit_verbosity` is the verbosity during training : 0 = silent, 1 = progress bar, 2 = one line per epoch"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"enhanced_dir = './data'\n",
"# enhanced_dir = f'{datasets_dir}/GTSRB/enhanced'\n",
"\n",
"dataset_name = 'set-24x24-L'\n",
"batch_size = 64\n",
"epochs = 5\n",
"scale = 1\n",
"fit_verbosity = 1"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Override parameters (batch mode) - Just forget this cell"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"fidle.override('enhanced_dir', 'dataset_name', 'batch_size', 'epochs', 'scale', 'fit_verbosity')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Step 2 - Load dataset\n",
"We're going to retrieve a previously recorded dataset. \n",
"For example: set-24x24-L"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"def read_dataset(enhanced_dir, dataset_name, scale=1):\n",
" '''\n",
" Reads h5 dataset\n",
" Args:\n",
" filename : datasets filename\n",
" dataset_name : dataset name, without .h5\n",
" Returns: \n",
" x_train,y_train, x_test,y_test data, x_meta,y_meta\n",
" '''\n",
"\n",
" # ---- Read dataset\n",
" #\n",
" chrono=fidle.Chrono()\n",
" chrono.start()\n",
" filename = f'{enhanced_dir}/{dataset_name}.h5'\n",
" with h5py.File(filename,'r') as f:\n",
" x_train = f['x_train'][:]\n",
" y_train = f['y_train'][:]\n",
" x_test = f['x_test'][:]\n",
" y_test = f['y_test'][:]\n",
" x_meta = f['x_meta'][:]\n",
" y_meta = f['y_meta'][:]\n",
"\n",
" # ---- Rescale \n",
" #\n",
" print('Original shape :', x_train.shape, y_train.shape)\n",
" x_train,y_train, x_test,y_test = fidle.utils.rescale_dataset(x_train,y_train,x_test,y_test, scale=scale)\n",
" print('Rescaled shape :', x_train.shape, y_train.shape)\n",
"\n",
" # ---- Shuffle\n",
" #\n",
" x_train,y_train=fidle.utils.shuffle_np_dataset(x_train,y_train)\n",
"\n",
" # ---- done\n",
" #\n",
" duration = chrono.get_delay()\n",
" size = fidle.utils.hsize(os.path.getsize(filename))\n",
" print(f'\\nDataset \"{dataset_name}\" is loaded and shuffled. ({size} in {duration})')\n",
" return x_train,y_train, x_test,y_test, x_meta,y_meta\n",
"\n",
"# ---- Read dataset\n",
"#\n",
"x_train,y_train,x_test,y_test, x_meta,y_meta = read_dataset(enhanced_dir, dataset_name, scale)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Step 3 - Have a look to the dataset\n",
"We take a quick look as we go by..."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"print(\"x_train : \", x_train.shape)\n",
"print(\"y_train : \", y_train.shape)\n",
"print(\"x_test : \", x_test.shape)\n",
"print(\"y_test : \", y_test.shape)\n",
"\n",
"fidle.scrawler.images(x_train, y_train, range(12), columns=6, x_size=2, y_size=2, save_as='01-dataset-medium')\n",
"fidle.scrawler.images(x_train, y_train, range(36), columns=12, x_size=1, y_size=1, save_as='02-dataset-small')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Step 4 - Create model\n",
"We will now build a model and train it...\n",
"\n",
"Some models :"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"\n",
"# ------------------------------------------------------------------\n",
"# -- A simple model, for 24x24 or 48x48 images --\n",
"# ------------------------------------------------------------------\n",
"#\n",
"def get_model_01(lx,ly,lz):\n",
" \n",
" model = keras.models.Sequential()\n",
"\n",
" model.add( keras.layers.Input((lx,ly,lz)) )\n",
" \n",
" model.add( keras.layers.Conv2D(96, (3,3), activation='relu' ))\n",
" model.add( keras.layers.MaxPooling2D((2, 2)))\n",
" model.add( keras.layers.Dropout(0.2))\n",
"\n",
" model.add( keras.layers.Conv2D(192, (3, 3), activation='relu'))\n",
" model.add( keras.layers.MaxPooling2D((2, 2)))\n",
" model.add( keras.layers.Dropout(0.2))\n",
"\n",
" model.add( keras.layers.Flatten()) \n",
" model.add( keras.layers.Dense(1500, activation='relu'))\n",
" model.add( keras.layers.Dropout(0.5))\n",
"\n",
" model.add( keras.layers.Dense(43, activation='softmax'))\n",
" return model\n",
" \n",
"\n",
"# ------------------------------------------------------------------\n",
"# -- A more sophisticated model, for 48x48 images --\n",
"# ------------------------------------------------------------------\n",
"#\n",
"def get_model_02(lx,ly,lz):\n",
" model = keras.models.Sequential()\n",
" \n",
" model.add( keras.layers.Input((lx,ly,lz)) )\n",
" \n",
" model.add( keras.layers.Conv2D(32, (3,3), activation='relu'))\n",
" model.add( keras.layers.MaxPooling2D((2, 2)))\n",
" model.add( keras.layers.Dropout(0.5))\n",
"\n",
" model.add( keras.layers.Conv2D(64, (3, 3), activation='relu'))\n",
" model.add( keras.layers.MaxPooling2D((2, 2)))\n",
" model.add( keras.layers.Dropout(0.5))\n",
"\n",
" model.add( keras.layers.Conv2D(128, (3, 3), activation='relu'))\n",
" model.add( keras.layers.MaxPooling2D((2, 2)))\n",
" model.add( keras.layers.Dropout(0.5))\n",
"\n",
" model.add( keras.layers.Conv2D(256, (3, 3), activation='relu'))\n",
" model.add( keras.layers.MaxPooling2D((2, 2)))\n",
" model.add( keras.layers.Dropout(0.5))\n",
"\n",
" model.add( keras.layers.Flatten()) \n",
" model.add( keras.layers.Dense(1152, activation='relu'))\n",
" model.add( keras.layers.Dropout(0.5))\n",
"\n",
" model.add( keras.layers.Dense(43, activation='softmax'))\n",
" return model\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Step 5 - Train the model\n",
"**Get the shape of my data :**"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"(n,lx,ly,lz) = x_train.shape\n",
"print(\"Images of the dataset have this folowing shape : \",(lx,ly,lz))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Get and compile a model, with the data shape :**"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"model = get_model_01(lx,ly,lz)\n",
"\n",
"model.summary()\n",
"\n",
"model.compile(optimizer = 'adam',\n",
" loss = 'sparse_categorical_crossentropy',\n",
" metrics = ['accuracy'])"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Train it :**"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"chrono=fidle.Chrono()\n",
"chrono.start()\n",
"\n",
"# ---- Shuffle train data\n",
"x_train,y_train=fidle.utils.shuffle_np_dataset(x_train,y_train)\n",
"\n",
"# ---- Train\n",
"history = model.fit( x_train, y_train,\n",
" batch_size = batch_size,\n",
" epochs = epochs,\n",
" verbose = fit_verbosity,\n",
" validation_data = (x_test, y_test))\n",
"\n",
"chrono.show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Step 5 - Evaluate"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"max_val_accuracy = max(history.history[\"val_accuracy\"])\n",
"print(\"Max validation accuracy is : {:.4f}\".format(max_val_accuracy))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"score = model.evaluate(x_test, y_test, verbose=0)\n",
"\n",
"print('Test loss : {:5.4f}'.format(score[0]))\n",
"print('Test accuracy : {:5.4f}'.format(score[1]))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"fidle.end()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"<div class=\"todo\">\n",
" What you can do:\n",
" <ul>\n",
" <li>Try the different models</li>\n",
" <li>Try with different datasets</li>\n",
" <li>Test different hyperparameters (epochs, batch size, optimization, etc.)</li>\n",
" <li>Create your own model</li>\n",
" </ul>\n",
"</div>"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"---\n",
"<img width=\"80px\" src=\"../fidle/img/logo-paysage.svg\"></img>"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3.9.2 ('fidle-env')",
"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": "3.9.2"
},
"vscode": {
"interpreter": {
"hash": "b3929042cc22c1274d74e3e946c52b845b57cb6d84f2d591ffe0519b38e4896d"
}
}
},
"nbformat": 4,
"nbformat_minor": 4
}