Newer
Older
{
"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",
"\n",
"Our main steps:\n",
" - Try n models with n datasets\n",
" - Write to be run in batch mode\n",
"execution_count": null,
"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",
"\n",
"from IPython.display import display\n",
"\n",
"VERSION='1.2'"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 2/ Init and start"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"print('\\nFull Convolutions Notebook')\n",
"print(' Version : {}'.format(VERSION))\n",
"print(' Run time : {}'.format(time.strftime(\"%A %-d %B %Y, %H:%M:%S\")))\n",
"print(' TensorFlow version :',tf.__version__)\n",
"print(' Keras version :',tf.keras.__version__)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
]
},
{
"cell_type": "code",
"execution_count": null,
"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) 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": [
]
},
{
"cell_type": "code",
"execution_count": null,
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
"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",
"# My sphisticated model, but small and fast\n",
"#\n",
"def get_model_v3(lx,ly,lz):\n",
" model = keras.models.Sequential()\n",
" model.add( keras.layers.Conv2D(32, (3,3), activation='relu', input_shape=(lx,ly,lz)))\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": [
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"def multi_run(datasets, models, batch_size=64, epochs=16):\n",
"\n",
" # ---- Columns of report\n",
" #\n",
" report={}\n",
" report['Dataset']=[]\n",
" report['Size'] =[]\n",
" for m in models:\n",
" report[m+' Accuracy'] = []\n",
" report[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",
" report['Dataset'].append(d_name)\n",
" report['Size'].append(d_size)\n",
" \n",
" # ---- Get the shape\n",
" (n,lx,ly,lz) = x_train.shape\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",
" # ---- Compile it\n",
" model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])\n",
" # ---- Callbacks tensorboard\n",
" log_dir = \"./run/logs/tb_{}_{}\".format(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(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",
" history = model.fit( x_train, y_train,\n",
" batch_size = batch_size,\n",
" epochs = epochs,\n",
" verbose = 0,\n",
" validation_data = (x_test, y_test),\n",
" callbacks = [tensorboard_callback, bestmodel_callback])\n",
" # ---- Result\n",
" end_time = time.time()\n",
" duration = end_time-start_time\n",
" accuracy = max(history.history[\"val_accuracy\"])*100\n",
" #\n",
" report[m_name+' Accuracy'].append(accuracy)\n",
" report[m_name+' Duration'].append(duration)\n",
" print(\"Accuracy={:.2f} and Duration={:.2f})\".format(accuracy,duration))\n",
" except:\n",
" report[m_name+' Accuracy'].append('-')\n",
" report[m_name+' Duration'].append('-')\n",
" print('-')\n",
" return report"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 6/ Run\n",
"### 6.1/ Clean"
]
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [
"%%bash\n",
"\n",
"/bin/rm -r ./run/logs 2>/dev/null\n",
"/bin/rm -r ./run/models 2>/dev/null\n",
"/bin/mkdir -p -m 755 ./run/logs\n",
"/bin/mkdir -p -m 755 ./run/models\n",
"echo -e \"\\nReset directories : ./run/logs and ./run/models .\""
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 6.2/ run and save report"
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%%time\n",
"\n",
"print('\\n---- Run','-'*50)\n",
"\n",
"# ---- Datasets and models list\n",
"# datasets = ['set-24x24-L', 'set-24x24-RGB']\n",
"# models = {'v1':get_model_v1, 'v3':get_model_v3}\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",
"report_name='./run/report-{}.json'.format(time.strftime(\"%Y-%m-%d_%Hh%Mm%Ss\"))\n",
"out = multi_run(datasets, models, batch_size=64, epochs=2)\n",
"with open(report_name, 'w') as outfile:\n",
" json.dump(out, outfile)\n",
"\n",
"print('\\nReport saved as ',report_name)\n",
"print('-'*59)\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
]
},
{
"execution_count": null,
"metadata": {},
"outputs": [],
"print('\\n{}'.format(time.strftime(\"%A %-d %B %Y, %H:%M:%S\")))\n",
"print(\"The work is done.\\n\")"
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
]
},
{
"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
}