{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"German Traffic Sign Recognition Benchmark (GTSRB)\n",
"=================================================\n",
"---\n",
"Introduction au Deep Learning (IDLE) - S. Arias, E. Maldonado, JL. Parouty - CNRS/SARI/DEVLOG - 2020 \n",
"\n",
"## Episode 5 : Full Convolutions\n",
"\n",
"Our main steps:\n",
" - Try n models with n datasets\n",
" - Save a Pandas/h5 report\n",
" - Write to be run in batch mode\n",
"\n",
"## 1/ Import"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"import tensorflow as tf\n",
"from tensorflow import keras\n",
"\n",
"import numpy as np\n",
"import h5py\n",
"import os,time,json\n",
"import random\n",
"\n",
"from IPython.display import display\n",
"\n",
"VERSION='1.6'"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 2/ Init and start"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"Full Convolutions Notebook\n",
" Version : 1.6\n",
" Now is : Tuesday 21 January 2020 - 00h11m24s\n",
" OAR id : ???\n",
" Tag id : 077605\n",
" Working directory : /home/pjluc/dev/fidle/GTSRB\n",
" TensorFlow version : 2.0.0\n",
" Keras version : 2.2.4-tf\n",
" for tensorboard : --logdir /home/pjluc/dev/fidle/GTSRB/run/logs_077605\n"
]
}
],
"source": [
"# ---- Where I am ?\n",
"now = time.strftime(\"%A %d %B %Y - %Hh%Mm%Ss\")\n",
"here = os.getcwd()\n",
"random.seed(time.time())\n",
"tag_id = '{:06}'.format(random.randint(0,99999))\n",
"\n",
"# ---- Who I am ?\n",
"if 'OAR_JOB_ID' in os.environ:\n",
" oar_id=os.environ['OAR_JOB_ID']\n",
"else:\n",
" oar_id='???'\n",
"\n",
"print('\\nFull Convolutions Notebook')\n",
"print(' Version : {}'.format(VERSION))\n",
"print(' Now is : {}'.format(now))\n",
"print(' OAR id : {}'.format(oar_id))\n",
"print(' Tag id : {}'.format(tag_id))\n",
"print(' Working directory : {}'.format(here))\n",
"print(' TensorFlow version :',tf.__version__)\n",
"print(' Keras version :',tf.keras.__version__)\n",
"print(' for tensorboard : --logdir {}/run/logs_{}'.format(here,tag_id))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 3/ Dataset loading"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"def read_dataset(name):\n",
" '''Reads h5 dataset from ./data\n",
"\n",
" Arguments: dataset name, without .h5\n",
" Returns: x_train,y_train,x_test,y_test data'''\n",
" # ---- Read dataset\n",
" filename='./data/'+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",
"\n",
" return x_train,y_train,x_test,y_test"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 4/ Models collection"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"\n",
"# A basic model\n",
"#\n",
"def get_model_v1(lx,ly,lz):\n",
" \n",
" model = keras.models.Sequential()\n",
" \n",
" model.add( keras.layers.Conv2D(96, (3,3), activation='relu', input_shape=(lx,ly,lz)))\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",
"# A more sophisticated model\n",
"#\n",
"def get_model_v2(lx,ly,lz):\n",
" model = keras.models.Sequential()\n",
"\n",
" model.add( keras.layers.Conv2D(64, (3, 3), padding='same', input_shape=(lx,ly,lz), activation='relu'))\n",
" model.add( keras.layers.Conv2D(64, (3, 3), activation='relu'))\n",
" model.add( keras.layers.MaxPooling2D(pool_size=(2, 2)))\n",
" model.add( keras.layers.Dropout(0.2))\n",
"\n",
" model.add( keras.layers.Conv2D(128, (3, 3), padding='same', activation='relu'))\n",
" model.add( keras.layers.Conv2D(128, (3, 3), activation='relu'))\n",
" model.add( keras.layers.MaxPooling2D(pool_size=(2, 2)))\n",
" model.add( keras.layers.Dropout(0.2))\n",
"\n",
" model.add( keras.layers.Conv2D(256, (3, 3), padding='same',activation='relu'))\n",
" model.add( keras.layers.Conv2D(256, (3, 3), activation='relu'))\n",
" model.add( keras.layers.MaxPooling2D(pool_size=(2, 2)))\n",
" model.add( keras.layers.Dropout(0.2))\n",
"\n",
" model.add( keras.layers.Flatten())\n",
" model.add( keras.layers.Dense(512, activation='relu'))\n",
" model.add( keras.layers.Dropout(0.5))\n",
" model.add( keras.layers.Dense(43, activation='softmax'))\n",
" return model\n",
"\n",
"def get_model_v3(lx,ly,lz):\n",
" model = keras.models.Sequential()\n",
" model.add(tf.keras.layers.Conv2D(32, (5, 5), padding='same', activation='relu', input_shape=(lx,ly,lz)))\n",
" model.add(tf.keras.layers.BatchNormalization(axis=-1)) \n",
" model.add(tf.keras.layers.MaxPooling2D(pool_size=(2, 2)))\n",
" model.add(tf.keras.layers.Dropout(0.2))\n",
"\n",
" model.add(tf.keras.layers.Conv2D(64, (5, 5), padding='same', activation='relu'))\n",
" model.add(tf.keras.layers.BatchNormalization(axis=-1))\n",
" model.add(tf.keras.layers.Conv2D(128, (5, 5), padding='same', activation='relu'))\n",
" model.add(tf.keras.layers.BatchNormalization(axis=-1))\n",
" model.add(tf.keras.layers.MaxPooling2D(pool_size=(2, 2)))\n",
" model.add(tf.keras.layers.Dropout(0.2))\n",
"\n",
" model.add(tf.keras.layers.Flatten())\n",
" model.add(tf.keras.layers.Dense(512, activation='relu'))\n",
" model.add(tf.keras.layers.BatchNormalization())\n",
" model.add(tf.keras.layers.Dropout(0.4))\n",
"\n",
" model.add(tf.keras.layers.Dense(43, activation='softmax'))\n",
" return model"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 5/ Multiple datasets, multiple models ;-)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
"def multi_run(datasets, models, datagen=None,\n",
" train_size=1, test_size=1, batch_size=64, epochs=16, \n",
" verbose=0, extension_dir='last'):\n",
"\n",
" # ---- Logs and models dir\n",
" #\n",
" os.makedirs('./run/logs_{}'.format(extension_dir), mode=0o750, exist_ok=True)\n",
" os.makedirs('./run/models_{}'.format(extension_dir), mode=0o750, exist_ok=True)\n",
" \n",
" # ---- Columns of output\n",
" #\n",
" output={}\n",
" output['Dataset']=[]\n",
" output['Size'] =[]\n",
" for m in models:\n",
" output[m+'_Accuracy'] = []\n",
" output[m+'_Duration'] = []\n",
"\n",
" # ---- Let's go\n",
" #\n",
" for d_name in datasets:\n",
" print(\"\\nDataset : \",d_name)\n",
"\n",
" # ---- Read dataset\n",
" x_train,y_train,x_test,y_test = read_dataset(d_name)\n",
" d_size=os.path.getsize('./data/'+d_name+'.h5')/(1024*1024)\n",
" output['Dataset'].append(d_name)\n",
" output['Size'].append(d_size)\n",
" \n",
" # ---- Get the shape\n",
" (n,lx,ly,lz) = x_train.shape\n",
" n_train = int(x_train.shape[0]*train_size)\n",
" n_test = int(x_test.shape[0]*test_size)\n",
"\n",
" # ---- For each model\n",
" for m_name,m_function in models.items():\n",
" print(\" Run model {} : \".format(m_name), end='')\n",
" # ---- get model\n",
" try:\n",
" model=m_function(lx,ly,lz)\n",
" # ---- Compile it\n",
" model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])\n",
" # ---- Callbacks tensorboard\n",
" log_dir = \"./run/logs_{}/tb_{}_{}\".format(extension_dir, d_name, m_name)\n",
" tensorboard_callback = tf.keras.callbacks.TensorBoard(log_dir=log_dir, histogram_freq=1)\n",
" # ---- Callbacks bestmodel\n",
" save_dir = \"./run/models_{}/model_{}_{}.h5\".format(extension_dir, d_name, m_name)\n",
" bestmodel_callback = tf.keras.callbacks.ModelCheckpoint(filepath=save_dir, verbose=0, monitor='accuracy', save_best_only=True)\n",
" # ---- Train\n",
" start_time = time.time()\n",
" if datagen==None:\n",
" # ---- No data augmentation (datagen=None) --------------------------------------\n",
" history = model.fit(x_train[:n_train], y_train[:n_train],\n",
" batch_size = batch_size,\n",
" epochs = epochs,\n",
" verbose = verbose,\n",
" validation_data = (x_test[:n_test], y_test[:n_test]),\n",
" callbacks = [tensorboard_callback, bestmodel_callback])\n",
" else:\n",
" # ---- Data augmentation (datagen given) ----------------------------------------\n",
" datagen.fit(x_train)\n",
" history = model.fit(datagen.flow(x_train, y_train, batch_size=batch_size),\n",
" steps_per_epoch = int(n_train/batch_size),\n",
" epochs = epochs,\n",
" verbose = verbose,\n",
" validation_data = (x_test[:n_test], y_test[:n_test]),\n",
" callbacks = [tensorboard_callback, bestmodel_callback])\n",
" \n",
" # ---- Result\n",
" end_time = time.time()\n",
" duration = end_time-start_time\n",
" accuracy = max(history.history[\"val_accuracy\"])*100\n",
" #\n",
" output[m_name+'_Accuracy'].append(accuracy)\n",
" output[m_name+'_Duration'].append(duration)\n",
" print(\"Accuracy={:.2f} and Duration={:.2f})\".format(accuracy,duration))\n",
" except:\n",
" output[m_name+'_Accuracy'].append('0')\n",
" output[m_name+'_Duration'].append('999')\n",
" print('-')\n",
" return output"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 6/ Run !"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"start_time = time.time()\n",
"\n",
"print('\\n---- Run','-'*50)\n",
"\n",
"# --------- Datasets, models, and more.. -----------------------------------\n",
"#\n",
"# ---- For tests\n",
"# datasets = ['set-24x24-L', 'set-24x24-RGB']\n",
"# models = {'v1':get_model_v1, 'v4':get_model_v2}\n",
"# batch_size = 64\n",
"# epochs = 2\n",
"# train_size = 0.1\n",
"# test_size = 0.1\n",
"# with_datagen = False\n",
"# verbose = 0\n",
"#\n",
"# ---- All possibilities -> Run A\n",
"# datasets = ['set-24x24-L', 'set-24x24-RGB', 'set-48x48-L', 'set-48x48-RGB', 'set-24x24-L-LHE', 'set-24x24-RGB-HE', 'set-48x48-L-LHE', 'set-48x48-RGB-HE']\n",
"# models = {'v1':get_model_v1, 'v2':get_model_v2, 'v3':get_model_v3}\n",
"# batch_size = 64\n",
"# epochs = 16\n",
"# train_size = 1\n",
"# test_size = 1\n",
"# with_datagen = False\n",
"# verbose = 0\n",
"#\n",
"# ---- Data augmentation -> Run B\n",
"datasets = ['set-48x48-RGB']\n",
"models = {'v2':get_model_v2}\n",
"batch_size = 64\n",
"epochs = 20\n",
"train_size = 1\n",
"test_size = 1\n",
"with_datagen = True\n",
"verbose = 0\n",
"#\n",
"# ---------------------------------------------------------------------------\n",
"\n",
"# ---- Data augmentation\n",
"#\n",
"if with_datagen :\n",
" datagen = keras.preprocessing.image.ImageDataGenerator(featurewise_center=False,\n",
" featurewise_std_normalization=False,\n",
" width_shift_range=0.1,\n",
" height_shift_range=0.1,\n",
" zoom_range=0.2,\n",
" shear_range=0.1,\n",
" rotation_range=10.)\n",
"else:\n",
" datagen=None\n",
" \n",
"# ---- Run\n",
"#\n",
"output = multi_run(datasets, models,\n",
" datagen=datagen,\n",
" train_size=train_size, test_size=test_size,\n",
" batch_size=batch_size, epochs=epochs,\n",
" verbose=verbose,\n",
" extension_dir=tag_id)\n",
"\n",
"# ---- Save report\n",
"#\n",
"report={}\n",
"report['output']=output\n",
"report['description']='train_size={} test_size={} batch_size={} epochs={} data_aug={}'.format(train_size,test_size,batch_size,epochs,with_datagen)\n",
"\n",
"report_name='./run/report_{}.json'.format(tag_id)\n",
"\n",
"with open(report_name, 'w') as file:\n",
" json.dump(report, file)\n",
"\n",
"print('\\nReport saved as ',report_name)\n",
"end_time = time.time()\n",
"duration = end_time-start_time\n",
"print('Duration : {} s'.format(duration))\n",
"print('-'*59)\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 7/ That's all folks.."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"print('\\n{}'.format(time.strftime(\"%A %-d %B %Y, %H:%M:%S\")))\n",
"print(\"The work is done.\\n\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.5"
}
},
"nbformat": 4,
"nbformat_minor": 4
}