-
Notifications
You must be signed in to change notification settings - Fork 0
/
train.py
272 lines (212 loc) · 7.9 KB
/
train.py
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
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
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
"""
Train our RNN on bottlecap or prediction files generated from our CNN.
"""
from keras.callbacks import TensorBoard, ModelCheckpoint, EarlyStopping, CSVLogger
from models import ResearchModels
from data import DataSet
import time
def train(data_type, seq_length, model, saved_model=None,
concat=False, class_limit=None, image_shape=None,
load_to_memory=False):
#Video-Classification-CNN-and-LSTM--master
#callbacks = [ EarlyStopping(monitor='val_loss', patience=10, verbose=0),
#ModelCheckpoint('video_1_LSTM_1_1024.h5', monitor='val_loss', save_best_only=True, verbose=0) ]
# nb_epoch = 500
# Set variables.
nb_epoch = 1000
batch_size = 32
checkpointer = ModelCheckpoint(
filepath='./data/checkpoints/' + model + '-' + data_type + \
'.{epoch:03d}-{val_loss:.3f}.hdf5',
verbose=1,
save_best_only=True)
# filepath='./data/checkpoints/try.hdf5',
# Helper: TensorBoard
tb = TensorBoard(log_dir='./data/logs')
# Helper: Stop when we stop learning.
early_stopper = EarlyStopping(patience=200)
# Helper: Save results.
timestamp = time.time()
csv_logger = CSVLogger('./data/logs/' + model + '-' + 'training-' + \
str(timestamp) + '.log')
# Get the data and process it.
if image_shape is None:
data = DataSet(
seq_length=seq_length,
class_limit=class_limit
)
else:
data = DataSet(
seq_length=seq_length,
class_limit=class_limit,
image_shape=image_shape
)
# Get samples per epoch.
# Multiply by 0.7 to attempt to guess how much of data.data is the train set.
steps_per_epoch = (len(data.data) * 0.7) // batch_size
if load_to_memory:
# Get data.
X, y = data.get_all_sequences_in_memory(batch_size, 'train', data_type, concat)
X_test, y_test = data.get_all_sequences_in_memory(batch_size, 'test', data_type, concat)
else:
# Get generators.
generator = data.frame_generator(batch_size, 'train', data_type, concat)
val_generator = data.frame_generator(batch_size, 'test', data_type, concat)
# Get the model.
rm = ResearchModels(len(data.classes), model, seq_length, saved_model)
#model.fit(train_data,train_labels,validation_data=(validation_data,validation_labels),
#batch_size=batch_size,nb_epoch=nb_epoch,callbacks=callbacks,shuffle=True,verbose=1)
# Fit!
if load_to_memory:
# Use standard fit.
rm.model.fit(
X,
y,
batch_size=batch_size,
validation_data=(X_test, y_test),
verbose=1,
callbacks=[checkpointer, tb, early_stopper, csv_logger],
epochs=nb_epoch
)
else:
# Use fit generator.
rm.model.fit_generator(
generator=generator,
steps_per_epoch=steps_per_epoch,
epochs=nb_epoch,
verbose=1,
callbacks=[checkpointer, tb, early_stopper, csv_logger],
validation_data=val_generator,
validation_steps=10)
def main():
"""These are the main training settings. Set each before running
this file."""
#model = 'lstm' # see `models.py` for more
model = 'lstm' # see `models.py` for morel
#saved_model = 'data\\checkpoints\\inception.016-0.52.hdf5' # None or weights file 고쳐봄!!!
#saved_model = 'data\\checkpoints\\vgg_128_32_lstm_model.h5' # None or weights file 고쳐봄!!!
saved_model = None
class_limit = None # int, can be 1-101 or None
seq_length = 80
load_to_memory = True # pre-load the sequences into memory
# Chose images or features and image shape based on network.
if model == 'conv_3d' or model == 'crnn':
data_type = 'images'
image_shape = (80, 80, 3)
load_to_memory = False
else:
data_type = 'features'
image_shape = None
# MLP requires flattened features.
if model == 'mlp':
concat = True
else:
concat = False
train(data_type, seq_length, model, saved_model=saved_model,
class_limit=class_limit, concat=concat, image_shape=image_shape,
load_to_memory=load_to_memory)
if __name__ == '__main__':
main()
'''
"""
Train our RNN on bottlecap or prediction files generated from our CNN.
"""
from keras.callbacks import TensorBoard, ModelCheckpoint, EarlyStopping, CSVLogger
from models import ResearchModels
from data import DataSet
import time
def train(data_type, seq_length, model, saved_model=None,
concat=False, class_limit=None, image_shape=None,
load_to_memory=False):
# Set variables.
nb_epoch = 5000
batch_size = 32
# Helper: Save the model.
checkpointer = ModelCheckpoint(
filepath='./data/checkpoints/' + model + '-' + data_type + \
'.{epoch:03d}-{val_loss:.3f}.hdf5',
verbose=1,
save_best_only=True)
# Helper: TensorBoard
tb = TensorBoard(log_dir='./data/logs')
# Helper: Stop when we stop learning.
# early_stopper = EarlyStopping(patience=10000)
# Helper: Save results.
timestamp = time.time()
csv_logger = CSVLogger('./data/logs/' + model + '-' + 'training-' + \
str(timestamp) + '.log')
# Get the data and process it.
if image_shape is None:
data = DataSet(
seq_length=seq_length,
class_limit=class_limit
)
else:
data = DataSet(
seq_length=seq_length,
class_limit=class_limit,
image_shape=image_shape
)
# Get samples per epoch.
# Multiply by 0.7 to attempt to guess how much of data.data is the train set.
steps_per_epoch = (len(data.data) * 0.7) // batch_size
if load_to_memory:
# Get data.
X, y = data.get_all_sequences_in_memory(batch_size, 'train', data_type, concat)
X_test, y_test = data.get_all_sequences_in_memory(batch_size, 'test', data_type, concat)
else:
# Get generators.
generator = data.frame_generator(batch_size, 'train', data_type, concat)
val_generator = data.frame_generator(batch_size, 'test', data_type, concat)
# Get the model.
rm = ResearchModels(len(data.classes), model, seq_length, saved_model)
# Fit!
if load_to_memory:
# Use standard fit.
rm.model.fit(
X,
y,
batch_size=batch_size,
validation_data=(X_test, y_test),
verbose=1,
callbacks=[checkpointer, tb, early_stopper, csv_logger],
epochs=nb_epoch
)
else:
# Use fit generator.
rm.model.fit_generator(
generator=generator,
steps_per_epoch=steps_per_epoch,
epochs=nb_epoch,
verbose=1,
callbacks=[checkpointer, tb, early_stopper, csv_logger],
validation_data=val_generator,
validation_steps=10)
def main():
"""These are the main training settings. Set each before running
this file."""
#model = 'lstm' # see `models.py` for more
model = 'lstm' # see `models.py` for morel
saved_model = None # None or weights file
class_limit = None # int, can be 1-101 or None
seq_length = 80
load_to_memory = True # pre-load the sequences into memory
# Chose images or features and image shape based on network.
if model == 'conv_3d' or model == 'crnn':
data_type = 'images'
image_shape = (80, 80, 3)
load_to_memory = False
else:
data_type = 'features'
image_shape = None
# MLP requires flattened features.
if model == 'mlp':
concat = True
else:
concat = False
train(data_type, seq_length, model, saved_model=saved_model,
class_limit=class_limit, concat=concat, image_shape=image_shape,
load_to_memory=load_to_memory)
if __name__ == '__main__':
main()
'''