-
Notifications
You must be signed in to change notification settings - Fork 7
/
main_multi.py
153 lines (119 loc) · 4.86 KB
/
main_multi.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
import os
import math
from termcolor import colored
import numpy as np
import matplotlib
matplotlib.use('Agg')
from data_helpers import load_data
from keras import callbacks
from keras.utils.vis_utils import plot_model
from matplotlib import pyplot as plt
from keras import backend as K
from capsule_net import CapsNet
def lambda1(epoch):
return 0.001 * np.exp(-epoch / 10.)
def lambda2(epoch):
initial_lrate = 0.1
k = 0.1
return k*initial_lrate/np.sqrt(epoch + K.epsilon())
def step_decay(epoch):
initial_lrate = 0.1
drop = 0.5
epochs_drop = 5
lrate = initial_lrate * math.pow(drop, math.floor((1+epoch)/epochs_drop))
return lrate
def margin_loss(y_true, y_pred):
L = y_true * K.square(K.maximum(0., 0.9 - y_pred)) + 0.5 * (1 - y_true) * K.square(K.maximum(0., y_pred - 0.1))
return K.mean(K.sum(L, 1))
def train(model, train, dev, test, save_directory, optimizer, epoch, batch_size, schedule):
(X_train, Y_train) = train
(X_dev, Y_dev) = dev
(X_test, Y_test) = test
# Callbacks
log = callbacks.CSVLogger(filename=save_directory + '/log.csv')
tb = callbacks.TensorBoard(log_dir=save_directory + '/tensorboard-logs', batch_size=batch_size)
checkpoint = callbacks.ModelCheckpoint(filepath=save_directory + '/weights-improvement-{epoch:02d}.hdf5',
save_best_only=True,
save_weights_only=True,
verbose=1)
lr_decay = callbacks.LearningRateScheduler(schedule=schedule, verbose=1)
# compile the model
model.compile(optimizer=optimizer,
loss=[margin_loss],
metrics=['accuracy'])
history = model.fit(x=X_train,
y=Y_train,
validation_data=[X_dev, Y_dev],
batch_size=batch_size,
epochs=epoch,
callbacks=[log, tb, checkpoint, lr_decay],
shuffle=True,
verbose=1)
score = model.evaluate(X_test, Y_test, batch_size=batch_size)
print colored(save_directory, 'green')
print colored(score, 'green')
print(history.history.keys())
# Summarize history for accuracy
plt.plot(history.history['acc'])
plt.plot(history.history['val_acc'])
plt.title('model accuracy')
plt.ylabel('accuracy')
plt.xlabel('epoch')
plt.legend(['training accuracy', 'testing accuracy'], loc='upper left')
plt.savefig(save_directory + '/model_accuracy.png')
plt.close()
# Summarize history for loss
plt.plot(history.history['loss'])
plt.plot(history.history['val_loss'])
plt.title('model loss')
plt.ylabel('loss')
plt.xlabel('epoch')
plt.legend(['training loss', 'testing loss'], loc='upper left')
plt.savefig(save_directory + '/model_loss.png')
plt.close()
model.save_weights(save_directory + '/trained_model.h5')
if __name__ == "__main__":
# Databases
databases = ["MR", "SST-1", "SST-2", "SUBJ", "TREC", "ProcCons", "IMDB"]
# Hyperparameters
optimizers = ['adam', 'nadam']
epochs = [10, 20]
batch_sizes = [200, 500]
schedules = [lambda1, lambda2, step_decay]
save_dir = './multi'
if not os.path.exists(save_dir):
os.makedirs(save_dir)
# Train
for d in databases:
print(d)
(x_train, y_train), (x_dev, y_dev), (x_test, y_test), vocab_size, max_len = load_data(d)
for o in optimizers:
for e in epochs:
for bz in batch_sizes:
for s in schedules:
model = CapsNet(input_shape=x_train.shape[1:],
n_class=len(np.unique(np.argmax(y_train, 1))),
num_routing=3,
vocab_size=vocab_size,
embed_dim=50,
max_len=max_len
)
model.summary()
plot_model(model, to_file=save_dir + '/model.png', show_shapes=True)
dir = save_dir + '/' + d
if not os.path.exists(dir):
os.makedirs(dir)
folder = dir + "/o=" + o + ",e=" + str(e) + ",bz=" + str(bz) + ",s=" + s.__name__
if not os.path.exists(folder):
os.makedirs(folder)
train(
model=model,
train=(x_train, y_train),
dev=(x_dev, y_dev),
test=(x_test, y_test),
save_directory=folder,
optimizer=o,
epoch=e,
batch_size=bz,
schedule=s
)