Newer
Older
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
{
"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",
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
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
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
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
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
"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
}