-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathmain.py
135 lines (113 loc) · 5.2 KB
/
main.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
import os
import sys
import numpy as np
import tensorflow as tf
from tqdm import tqdm
from config import cfg
from utils import load_data
from capsNetNotMNIST import CapsNetNotMNIST
from capsNetAffNIST import CapsNetAffNIST
def save_to():
if not os.path.exists(cfg.results):
os.mkdir(cfg.results)
if cfg.is_training:
loss = cfg.results + '/loss.csv'
train_acc = cfg.results + '/train_acc.csv'
val_acc = cfg.results + '/val_acc.csv'
if os.path.exists(val_acc):
os.remove(val_acc)
if os.path.exists(loss):
os.remove(loss)
if os.path.exists(train_acc):
os.remove(train_acc)
fd_train_acc = open(train_acc, 'w')
fd_train_acc.write('step,train_acc\n')
fd_loss = open(loss, 'w')
fd_loss.write('step,loss\n')
fd_val_acc = open(val_acc, 'w')
fd_val_acc.write('step,val_acc\n')
return(fd_train_acc, fd_loss, fd_val_acc)
else:
test_acc = cfg.results + '/test_acc.csv'
if os.path.exists(test_acc):
os.remove(test_acc)
fd_test_acc = open(test_acc, 'w')
fd_test_acc.write('test_acc\n')
return(fd_test_acc)
def train(model, supervisor, num_label):
trX, trY, num_tr_batch, valX, valY, num_val_batch = load_data(cfg.dataset, cfg.batch_size, is_training=True)
Y = valY[:num_val_batch * cfg.batch_size].reshape((-1, 1))
fd_train_acc, fd_loss, fd_val_acc = save_to()
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
with supervisor.managed_session(config=config) as sess:
print("\nNote: all of results will be saved to directory: " + cfg.results)
for epoch in range(cfg.epoch):
sys.stdout.write('Training for epoch ' + str(epoch) + '/' + str(cfg.epoch) + ':')
sys.stdout.flush()
if supervisor.should_stop():
print('supervisor stoped!')
break
for step in tqdm(range(num_tr_batch), total=num_tr_batch, ncols=70, leave=False, unit='b'):
start = step * cfg.batch_size
end = start + cfg.batch_size
global_step = epoch * num_tr_batch + step
if global_step % cfg.train_sum_freq == 0:
_, loss, train_acc, summary_str = sess.run([model.train_op, model.total_loss, model.accuracy, model.train_summary])
assert not np.isnan(loss), 'Something wrong! loss is nan...'
supervisor.summary_writer.add_summary(summary_str, global_step)
fd_loss.write(str(global_step) + ',' + str(loss) + "\n")
fd_loss.flush()
fd_train_acc.write(str(global_step) + ',' + str(train_acc / cfg.batch_size) + "\n")
fd_train_acc.flush()
else:
sess.run(model.train_op)
if cfg.val_sum_freq != 0 and (global_step) % cfg.val_sum_freq == 0:
val_acc = 0
for i in range(num_val_batch):
start = i * cfg.batch_size
end = start + cfg.batch_size
acc = sess.run(model.accuracy, {model.X: valX[start:end], model.labels: valY[start:end]})
val_acc += acc
val_acc = val_acc / (cfg.batch_size * num_val_batch)
fd_val_acc.write(str(global_step) + ',' + str(val_acc) + '\n')
fd_val_acc.flush()
if (epoch + 1) % cfg.save_freq == 0:
supervisor.saver.save(sess, cfg.logdir + '/model_epoch_%04d_step_%02d' % (epoch, global_step))
fd_val_acc.close()
fd_train_acc.close()
fd_loss.close()
def evaluation(model, supervisor, num_label):
teX, teY, num_te_batch = load_data(cfg.dataset, cfg.batch_size, is_training=False)
fd_test_acc = save_to()
with supervisor.managed_session(config=tf.ConfigProto(allow_soft_placement=True)) as sess:
supervisor.saver.restore(sess, tf.train.latest_checkpoint(cfg.logdir))
tf.logging.info('Model restored!')
test_acc = 0
for i in tqdm(range(num_te_batch), total=num_te_batch, ncols=70, leave=False, unit='b'):
start = i * cfg.batch_size
end = start + cfg.batch_size
acc = sess.run(model.accuracy, {model.X: teX[start:end], model.labels: teY[start:end]})
test_acc += acc
test_acc = test_acc / (cfg.batch_size * num_te_batch)
fd_test_acc.write(str(test_acc))
fd_test_acc.close()
print('Test accuracy has been saved to ' + cfg.results + '/test_accuracy.txt')
def main(_):
tf.logging.info(' Loading Graph...')
num_label = 10
print("The dataset is :"+cfg.dataset)
if cfg.dataset=="notMNIST":
model = CapsNetNotMNIST()
elif cfg.dataset=="affNIST":
model = CapsNetAffNIST()
tf.logging.info(' Graph loaded')
sv = tf.train.Supervisor(graph=model.graph, logdir=cfg.logdir, save_model_secs=0)
if cfg.is_training:
tf.logging.info(' Start trainging...')
train(model, sv, num_label)
tf.logging.info('Training done')
else:
evaluation(model, sv, num_label)
if __name__ == "__main__":
tf.app.run()