{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"<img width=\"800px\" src=\"../fidle/img/header.svg\"></img>\n",
"\n",
"# <!-- TITLE --> [K3GTSRB3] - Training monitoring\n",
"<!-- DESC --> Episode 3 : Monitoring, analysis and check points during a training session, using Keras3\n",
"<!-- AUTHOR : Jean-Luc Parouty (CNRS/SIMaP) -->\n",
"\n",
"## Objectives :\n",
" - **Understand** what happens during the **training** process\n",
" - Implement **monitoring**, **backup** and **recovery** solutions\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",
"Description is available there : http://benchmark.ini.rub.de/?section=gtsrb&subsection=dataset\n",
"\n",
"## What we're going to do :\n",
"\n",
" - Monitoring and understanding our model training \n",
" - Add recovery points\n",
" - Analyze the results \n",
" - Restore and run recovery points \n",
"\n",
"## Step 1 - Import and init\n",
"### 1.1 - Python stuffs"
]
},
{
"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 os, random\n",
"\n",
"import fidle\n",
"\n",
"import modules.my_loader as my_loader\n",
"import modules.my_models as my_models\n",
"import modules.my_tools as my_tools\n",
"from modules.my_TensorboardCallback import TensorboardCallback\n",
"\n",
"\n",
"# Init Fidle environment\n",
"run_id, run_dir, datasets_dir = fidle.init('K3GTSRB3')"
]
},
{
"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 L dataset, 10 epochs, 20% dataset, need 1'30 on a CPU laptop. (Accuracy=91.4)\\\n",
"A 20% 48x48 RGB dataset, 10 epochs, 20% dataset, need 6'30s on a CPU laptop. (Accuracy=91.5)\\\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",
"model_name = 'model_01'\n",
"dataset_name = 'set-24x24-L'\n",
"batch_size = 64\n",
"epochs = 10\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', 'model_name', 'dataset_name', 'batch_size', 'epochs', 'scale', 'fit_verbosity')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Step 2 - Load dataset\n",
"Dataset is one of the saved dataset..."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"x_train,y_train,x_test,y_test, x_meta,y_meta = my_loader.read_dataset(enhanced_dir, dataset_name, scale)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Step 3 - Have a look to the dataset"
]
},
{
"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(24), columns=8, x_size=1, y_size=1, save_as='02-dataset-small')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Step 4 - Get a model"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"(n,lx,ly,lz) = x_train.shape\n",
"\n",
"model = my_models.get_model( model_name, lx,ly,lz )\n",
"model.summary()\n",
"\n",
"model.compile(optimizer='adam',\n",
" loss='sparse_categorical_crossentropy',\n",
" metrics=['accuracy'])"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Step 5 - Prepare callbacks \n",
"We will add 2 callbacks : \n",
"\n",
"**TensorBoard** \n",
"Training logs, which can be visualised using [Tensorboard tool](https://www.tensorflow.org/tensorboard). \n",
"\n",
"**Model backup** \n",
" It is possible to save the model each xx epoch or at each improvement. \n",
" The model can be saved completely or partially (weight). \n",
" See [Keras documentation](https://keras.io/api/callbacks/)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"fidle.utils.mkdir(run_dir + '/models')\n",
"fidle.utils.mkdir(run_dir + '/logs')\n",
"\n",
"# ---- Callback for tensorboard (This one is homemade !)\n",
"#\n",
"tenseorboard_callback = TensorboardCallback(\n",
" log_dir=run_dir + \"/logs/tb_\" + fidle.Chrono.tag_now())\n",
"\n",
"# ---- Callback to save best model\n",
"#\n",
"bestmodel_callback = keras.callbacks.ModelCheckpoint( \n",
" filepath= run_dir + \"/models/best-model.keras\",\n",
" monitor='val_accuracy', \n",
" mode='max', \n",
" save_best_only=True)\n",
"\n",
"# ---- Callback to save model from each epochs\n",
"#\n",
"savemodel_callback = keras.callbacks.ModelCheckpoint(\n",
" filepath= run_dir + \"/models/{epoch:02d}.keras\",\n",
" save_freq=\"epoch\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Step 6 - Train the model"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# %load_ext tensorboard\n",
"# %tensorboard --logdir ./run/K3GTSRB3/logs"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Train it :** \n",
"Note: The training curve is visible in real time with Tensorboard (see step 5)"
]
},
{
"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",
"# Note: To be faster in our example, we can take only 2000 values\n",
"#\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",
" callbacks=[tenseorboard_callback, bestmodel_callback, savemodel_callback] )\n",
"\n",
"model.save(f'{run_dir}/models/last-model.keras')\n",
"\n",
"chrono.show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Evaluate it :**"
]
},
{
"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": "markdown",
"metadata": {},
"source": [
"## Step 7 - History\n",
"The return of model.fit() returns us the learning history"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"fidle.scrawler.history(history, save_as='03-history')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Step 8 - Evaluation and confusion"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"y_sigmoid = model.predict(x_test, verbose=fit_verbosity)\n",
"y_pred = np.argmax(y_sigmoid, axis=-1)\n",
"\n",
"fidle.scrawler.confusion_matrix(y_test,y_pred,range(43), figsize=(12, 12),normalize=False, save_as='04-confusion-matrix')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Step 9 - Restore and evaluate\n",
"#### List saved models :"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# !ls -1rt \"$run_dir\"/models/"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Restore a model :"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"loaded_model = keras.models.load_model(f'{run_dir}/models/best-model.keras')\n",
"# loaded_model.summary()\n",
"print(\"Loaded.\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Evaluate it :"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"score = loaded_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": "markdown",
"metadata": {},
"source": [
"#### Make a prediction :"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# ---- Pick a random image\n",
"#\n",
"i = random.randint(1,len(x_test))\n",
"x,y = x_test[i], y_test[i]\n",
"\n",
"# ---- Do prediction\n",
"#\n",
"prediction = loaded_model.predict( np.array([x]), verbose=fit_verbosity )\n",
"\n",
"# ---- Show result\n",
"\n",
"my_tools.show_prediction( prediction, x, y, x_meta )"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"fidle.end()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Step 10 - To go further ;-)\n",
"What you can do:\n",
"- Try differents models\n",
"- Use a subset of the dataset\n",
"- Try different datasets\n",
"- Try to recognize exotic signs !\n",
"- Test different hyperparameters (epochs, batch size, optimization, etc.\n",
" "
]
},
{
"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
}