質問編集履歴
3
質問の再掲
test
CHANGED
File without changes
|
test
CHANGED
File without changes
|
2
質問の変更
test
CHANGED
@@ -1 +1 @@
|
|
1
|
-
Chainer
|
1
|
+
ChainerのValueErrorを解消したい
|
test
CHANGED
@@ -1,511 +1,463 @@
|
|
1
|
-
chainerを使って、簡単なCNNを実装したいのですが、
|
1
|
+
chainerを使って、簡単なCNNを実装したいのですが、ValueErrorがでてしまい、調べてみましたが、Errorの解消方法が分かりません。
|
2
|
+
|
3
|
+
どうすればよいのでしょうか?
|
4
|
+
|
5
|
+
|
6
|
+
|
7
|
+
#ソースコード
|
8
|
+
|
9
|
+
```python
|
10
|
+
|
11
|
+
import numpy as np
|
12
|
+
|
13
|
+
#from keras.utils import np_utils
|
14
|
+
|
15
|
+
import sys, os
|
16
|
+
|
17
|
+
import six
|
18
|
+
|
19
|
+
import argparse
|
20
|
+
|
21
|
+
import chainer
|
22
|
+
|
23
|
+
import chainer.links as L
|
24
|
+
|
25
|
+
from chainer import optimizers, cuda, serializers
|
26
|
+
|
27
|
+
import chainer.functions as F
|
28
|
+
|
29
|
+
|
30
|
+
|
31
|
+
from CNNSC import CNNSC
|
32
|
+
|
33
|
+
|
34
|
+
|
35
|
+
def get_parser():
|
36
|
+
|
37
|
+
|
38
|
+
|
39
|
+
DEF_GPU = -1
|
40
|
+
|
41
|
+
DEF_DATA = "..{sep}Data{sep}input.dat".format(sep=os.sep)
|
42
|
+
|
43
|
+
DEF_EPOCH = 100
|
44
|
+
|
45
|
+
DEF_BATCHSIZE = 50
|
46
|
+
|
47
|
+
|
48
|
+
|
49
|
+
#引数の設定
|
50
|
+
|
51
|
+
parser = argparse.ArgumentParser()
|
52
|
+
|
53
|
+
parser.add_argument('--gpu',
|
54
|
+
|
55
|
+
dest='gpu',
|
56
|
+
|
57
|
+
type=int,
|
58
|
+
|
59
|
+
default=DEF_GPU,
|
60
|
+
|
61
|
+
metavar='CORE_NUMBER',
|
62
|
+
|
63
|
+
help='use CORE_NUMBER gpu (default: use cpu)')
|
64
|
+
|
65
|
+
parser.add_argument('--epoch',
|
66
|
+
|
67
|
+
dest='epoch',
|
68
|
+
|
69
|
+
type=int,
|
70
|
+
|
71
|
+
default=DEF_EPOCH,
|
72
|
+
|
73
|
+
help='number of epochs to learn')
|
74
|
+
|
75
|
+
parser.add_argument('--batchsize',
|
76
|
+
|
77
|
+
dest='batchsize',
|
78
|
+
|
79
|
+
type=int,
|
80
|
+
|
81
|
+
default=DEF_BATCHSIZE,
|
82
|
+
|
83
|
+
help='learning minibatch size')
|
84
|
+
|
85
|
+
parser.add_argument('--save-model',
|
86
|
+
|
87
|
+
dest='save_model',
|
88
|
+
|
89
|
+
action='store',
|
90
|
+
|
91
|
+
type=str,
|
92
|
+
|
93
|
+
default=None,
|
94
|
+
|
95
|
+
metavar='PATH',
|
96
|
+
|
97
|
+
help='save model to PATH')
|
98
|
+
|
99
|
+
parser.add_argument('--save-optimizer',
|
100
|
+
|
101
|
+
dest='save_optimizer',
|
102
|
+
|
103
|
+
action='store',
|
104
|
+
|
105
|
+
type=str,
|
106
|
+
|
107
|
+
default=None,
|
108
|
+
|
109
|
+
metavar='PATH',
|
110
|
+
|
111
|
+
help='save optimizer to PATH')
|
112
|
+
|
113
|
+
parser.add_argument('--baseline',
|
114
|
+
|
115
|
+
dest='baseline',
|
116
|
+
|
117
|
+
action='store_true',
|
118
|
+
|
119
|
+
help='if true, run baseline model')
|
120
|
+
|
121
|
+
|
122
|
+
|
123
|
+
return parser
|
124
|
+
|
125
|
+
|
126
|
+
|
127
|
+
def save_model(model, file_path='sc_cnn.model'):
|
128
|
+
|
129
|
+
# modelを保存
|
130
|
+
|
131
|
+
print ('save the model')
|
132
|
+
|
133
|
+
model.to_cpu()
|
134
|
+
|
135
|
+
serializers.save_npz(file_path, model)
|
136
|
+
|
137
|
+
|
138
|
+
|
139
|
+
def save_optimizer(optimizer, file_path='sc_cnn.state'):
|
140
|
+
|
141
|
+
# optimizerを保存
|
142
|
+
|
143
|
+
print ('save the optimizer')
|
144
|
+
|
145
|
+
serializers.save_npz(file_path, optimizer)
|
146
|
+
|
147
|
+
|
148
|
+
|
149
|
+
def train(args):
|
150
|
+
|
151
|
+
|
152
|
+
|
153
|
+
batchsize = args.batchsize # minibatch size
|
154
|
+
|
155
|
+
n_epoch = args.epoch # エポック数
|
156
|
+
|
157
|
+
|
158
|
+
|
159
|
+
height = 100
|
160
|
+
|
161
|
+
width = 200
|
162
|
+
|
163
|
+
|
164
|
+
|
165
|
+
#訓練データの読み込み
|
166
|
+
|
167
|
+
x_train = np.load('posneg_train_data.npy')
|
168
|
+
|
169
|
+
y_train = np.load('posneg_train_label.npy')
|
170
|
+
|
171
|
+
|
172
|
+
|
173
|
+
#one_hot_y_train = np_utils.to_categorical(y_train)
|
174
|
+
|
175
|
+
|
176
|
+
|
177
|
+
#テストデータの読み込み
|
178
|
+
|
179
|
+
x_test = np.load('posneg_test_data.npy')
|
180
|
+
|
181
|
+
y_test = np.load('posneg_test_label.npy')
|
182
|
+
|
183
|
+
|
184
|
+
|
185
|
+
#one_hot_y_test = np_utils.to_categorical(y_test)
|
186
|
+
|
187
|
+
|
188
|
+
|
189
|
+
N_test = y_test.size # test data size
|
190
|
+
|
191
|
+
N = len(x_train) # train data size
|
192
|
+
|
193
|
+
in_units = x_train.shape[1] # 入力層のユニット数 (語彙数)
|
194
|
+
|
195
|
+
|
196
|
+
|
197
|
+
# (nsample, channel, height, width) の4次元テンソルに変換
|
198
|
+
|
199
|
+
input_channel = 1
|
200
|
+
|
201
|
+
x_train = x_train.reshape(len(x_train), input_channel, height, width)
|
202
|
+
|
203
|
+
x_test = x_test.reshape(len(x_test), input_channel, height, width)
|
204
|
+
|
205
|
+
|
206
|
+
|
207
|
+
n_label = 2 # ラベル数
|
208
|
+
|
209
|
+
filter_height = [3,4,5] # フィルタの高さ
|
210
|
+
|
211
|
+
baseline_filter_height = [3]
|
212
|
+
|
213
|
+
filter_width = width # フィルタの幅 (embeddingの次元数)
|
214
|
+
|
215
|
+
output_channel = 100
|
216
|
+
|
217
|
+
decay = 0.0001 # 重み減衰
|
218
|
+
|
219
|
+
grad_clip = 3 # gradient norm threshold to clip
|
220
|
+
|
221
|
+
max_sentence_len = height # max length of sentences
|
222
|
+
|
223
|
+
|
224
|
+
|
225
|
+
# モデルの定義
|
226
|
+
|
227
|
+
if args.baseline == False:
|
228
|
+
|
229
|
+
# 提案モデル
|
230
|
+
|
231
|
+
model = CNNSC(input_channel,
|
232
|
+
|
233
|
+
output_channel,
|
234
|
+
|
235
|
+
filter_height,
|
236
|
+
|
237
|
+
filter_width,
|
238
|
+
|
239
|
+
n_label,
|
240
|
+
|
241
|
+
max_sentence_len)
|
242
|
+
|
243
|
+
else:
|
244
|
+
|
245
|
+
# ベースラインモデル (フィルタの種類が1つ)
|
246
|
+
|
247
|
+
model = CNNSC(input_channel,
|
248
|
+
|
249
|
+
output_channel,
|
250
|
+
|
251
|
+
baseline_filter_height,
|
252
|
+
|
253
|
+
filter_width,
|
254
|
+
|
255
|
+
n_label,
|
256
|
+
|
257
|
+
max_sentence_len)
|
258
|
+
|
259
|
+
|
260
|
+
|
261
|
+
# Setup optimizer
|
262
|
+
|
263
|
+
optimizer = optimizers.AdaDelta()
|
264
|
+
|
265
|
+
optimizer.setup(model)
|
266
|
+
|
267
|
+
optimizer.add_hook(chainer.optimizer.GradientClipping(grad_clip))
|
268
|
+
|
269
|
+
optimizer.add_hook(chainer.optimizer.WeightDecay(decay))
|
270
|
+
|
271
|
+
|
272
|
+
|
273
|
+
#GPUを使うかどうか
|
274
|
+
|
275
|
+
if args.gpu >= 0:
|
276
|
+
|
277
|
+
cuda.check_cuda_available()
|
278
|
+
|
279
|
+
cuda.get_device(args.gpu).use()
|
280
|
+
|
281
|
+
model.to_gpu()
|
282
|
+
|
283
|
+
xp = np if args.gpu < 0 else cuda.cupy #args.gpu <= 0: use cpu, otherwise: use gpu
|
284
|
+
|
285
|
+
|
286
|
+
|
287
|
+
# Learning loop
|
288
|
+
|
289
|
+
for epoch in six.moves.range(1, n_epoch + 1):
|
290
|
+
|
291
|
+
|
292
|
+
|
293
|
+
print ('epoch', epoch, '/', n_epoch)
|
294
|
+
|
295
|
+
|
296
|
+
|
297
|
+
# training
|
298
|
+
|
299
|
+
perm = np.random.permutation(N) #ランダムな整数列リストを取得
|
300
|
+
|
301
|
+
sum_train_loss = 0.0
|
302
|
+
|
303
|
+
sum_train_accuracy = 0.0
|
304
|
+
|
305
|
+
for i in six.moves.range(0, N, batchsize):
|
306
|
+
|
307
|
+
|
308
|
+
|
309
|
+
#perm を使い x_train, y_trainからデータセットを選択 (毎回対象となるデータは異なる)
|
310
|
+
|
311
|
+
x = chainer.Variable(xp.asarray(x_train[perm[i:i + batchsize]]).astype(np.float32)) #source
|
312
|
+
|
313
|
+
t = chainer.Variable(xp.asarray(y_train[perm[i:i + batchsize]]).astype(np.float32)) #target
|
314
|
+
|
315
|
+
|
316
|
+
|
317
|
+
model.zerograds()
|
318
|
+
|
319
|
+
|
320
|
+
|
321
|
+
y = model(x)
|
322
|
+
|
323
|
+
loss = F.softmax_cross_entropy(y, t) # 損失の計算
|
324
|
+
|
325
|
+
accuracy = F.accuracy(y, t) # 正解率の計算
|
326
|
+
|
327
|
+
|
328
|
+
|
329
|
+
sum_train_loss += loss.data * len(t)
|
330
|
+
|
331
|
+
sum_train_accuracy += accuracy.data * len(t)
|
332
|
+
|
333
|
+
|
334
|
+
|
335
|
+
# 最適化を実行
|
336
|
+
|
337
|
+
loss.backward()
|
338
|
+
|
339
|
+
optimizer.update()
|
340
|
+
|
341
|
+
|
342
|
+
|
343
|
+
print('train mean loss={}, accuracy={}'.format(sum_train_loss / N, sum_train_accuracy / N)) #平均誤差
|
344
|
+
|
345
|
+
|
346
|
+
|
347
|
+
# evaluation
|
348
|
+
|
349
|
+
sum_test_loss = 0.0
|
350
|
+
|
351
|
+
sum_test_accuracy = 0.0
|
352
|
+
|
353
|
+
for i in six.moves.range(0, N_test, batchsize):
|
354
|
+
|
355
|
+
|
356
|
+
|
357
|
+
# all test data
|
358
|
+
|
359
|
+
x = chainer.Variable(xp.asarray(x_test[i:i + batchsize]).astype(np.float32))
|
360
|
+
|
361
|
+
t = chainer.Variable(xp.asarray(y_test[i:i + batchsize]).astype(np.float32))
|
362
|
+
|
363
|
+
|
364
|
+
|
365
|
+
y = model(x, False)
|
366
|
+
|
367
|
+
loss = F.softmax_cross_entropy(y, t) # 損失の計算
|
368
|
+
|
369
|
+
accuracy = F.accuracy(y, t) # 正解率の計算
|
370
|
+
|
371
|
+
|
372
|
+
|
373
|
+
sum_test_loss += loss.data * len(t)
|
374
|
+
|
375
|
+
sum_test_accuracy += accuracy.data * len(t)
|
376
|
+
|
377
|
+
|
378
|
+
|
379
|
+
print(' test mean loss={}, accuracy={}'.format(sum_test_loss / N_test, sum_test_accuracy / N_test)) #平均誤差
|
380
|
+
|
381
|
+
|
382
|
+
|
383
|
+
sys.stdout.flush()
|
384
|
+
|
385
|
+
|
386
|
+
|
387
|
+
return model, optimizer
|
388
|
+
|
389
|
+
|
390
|
+
|
391
|
+
def main():
|
392
|
+
|
393
|
+
parser = get_parser()
|
394
|
+
|
395
|
+
args = parser.parse_args()
|
396
|
+
|
397
|
+
model, optimizer = train(args)
|
398
|
+
|
399
|
+
|
400
|
+
|
401
|
+
if args.save_model != None:
|
402
|
+
|
403
|
+
save_model(model)
|
404
|
+
|
405
|
+
if args.save_optimizer != None:
|
406
|
+
|
407
|
+
save_optimizer(optimizer)
|
408
|
+
|
409
|
+
|
410
|
+
|
411
|
+
if __name__ == "__main__":
|
412
|
+
|
413
|
+
main()
|
2
414
|
|
3
415
|
```
|
4
416
|
|
5
|
-
|
417
|
+
|
6
|
-
|
7
|
-
|
418
|
+
|
8
|
-
|
9
|
-
x_test.astype(np.float32)
|
10
|
-
|
11
|
-
|
419
|
+
#エラーメッセージ
|
12
420
|
|
13
421
|
```
|
14
422
|
|
15
|
-
|
16
|
-
|
17
|
-
|
18
|
-
|
19
|
-
|
20
|
-
|
21
|
-
|
22
|
-
|
23
|
-
|
24
|
-
|
25
|
-
|
26
|
-
|
27
|
-
import numpy as np
|
28
|
-
|
29
|
-
import sys, os
|
30
|
-
|
31
|
-
import six
|
32
|
-
|
33
|
-
import argparse
|
34
|
-
|
35
|
-
import chainer
|
36
|
-
|
37
|
-
import chainer.links as L
|
38
|
-
|
39
|
-
from chainer import optimizers, cuda, serializers
|
40
|
-
|
41
|
-
import chainer.functions as F
|
42
|
-
|
43
|
-
|
44
|
-
|
45
|
-
from CNNSC import CNNSC
|
46
|
-
|
47
|
-
|
48
|
-
|
49
|
-
def get_parser():
|
50
|
-
|
51
|
-
|
52
|
-
|
53
|
-
DEF_GPU = -1
|
54
|
-
|
55
|
-
DEF_DATA = "..{sep}Data{sep}input.dat".format(sep=os.sep)
|
56
|
-
|
57
|
-
DEF_EPOCH = 100
|
58
|
-
|
59
|
-
DEF_BATCHSIZE = 50
|
60
|
-
|
61
|
-
|
62
|
-
|
63
|
-
#引数の設定
|
64
|
-
|
65
|
-
parser = argparse.ArgumentParser()
|
66
|
-
|
67
|
-
parser.add_argument('--gpu',
|
68
|
-
|
69
|
-
dest='gpu',
|
70
|
-
|
71
|
-
type=int,
|
72
|
-
|
73
|
-
default=DEF_GPU,
|
74
|
-
|
75
|
-
metavar='CORE_NUMBER',
|
76
|
-
|
77
|
-
help='use CORE_NUMBER gpu (default: use cpu)')
|
78
|
-
|
79
|
-
parser.add_argument('--epoch',
|
80
|
-
|
81
|
-
dest='epoch',
|
82
|
-
|
83
|
-
type=int,
|
84
|
-
|
85
|
-
default=DEF_EPOCH,
|
86
|
-
|
87
|
-
help='number of epochs to learn')
|
88
|
-
|
89
|
-
parser.add_argument('--batchsize',
|
90
|
-
|
91
|
-
dest='batchsize',
|
92
|
-
|
93
|
-
type=int,
|
94
|
-
|
95
|
-
default=DEF_BATCHSIZE,
|
96
|
-
|
97
|
-
help='learning minibatch size')
|
98
|
-
|
99
|
-
parser.add_argument('--save-model',
|
100
|
-
|
101
|
-
dest='save_model',
|
102
|
-
|
103
|
-
action='store',
|
104
|
-
|
105
|
-
type=str,
|
106
|
-
|
107
|
-
default=None,
|
108
|
-
|
109
|
-
metavar='PATH',
|
110
|
-
|
111
|
-
help='save model to PATH')
|
112
|
-
|
113
|
-
parser.add_argument('--save-optimizer',
|
114
|
-
|
115
|
-
dest='save_optimizer',
|
116
|
-
|
117
|
-
action='store',
|
118
|
-
|
119
|
-
type=str,
|
120
|
-
|
121
|
-
default=None,
|
122
|
-
|
123
|
-
metavar='PATH',
|
124
|
-
|
125
|
-
help='save optimizer to PATH')
|
126
|
-
|
127
|
-
parser.add_argument('--baseline',
|
128
|
-
|
129
|
-
dest='baseline',
|
130
|
-
|
131
|
-
action='store_true',
|
132
|
-
|
133
|
-
help='if true, run baseline model')
|
134
|
-
|
135
|
-
|
136
|
-
|
137
|
-
return parser
|
138
|
-
|
139
|
-
|
140
|
-
|
141
|
-
def save_model(model, file_path='sc_cnn.model'):
|
142
|
-
|
143
|
-
# modelを保存
|
144
|
-
|
145
|
-
print ('save the model')
|
146
|
-
|
147
|
-
model.to_cpu()
|
148
|
-
|
149
|
-
serializers.save_npz(file_path, model)
|
150
|
-
|
151
|
-
|
152
|
-
|
153
|
-
def save_optimizer(optimizer, file_path='sc_cnn.state'):
|
154
|
-
|
155
|
-
# optimizerを保存
|
156
|
-
|
157
|
-
print ('save the optimizer')
|
158
|
-
|
159
|
-
serializers.save_npz(file_path, optimizer)
|
160
|
-
|
161
|
-
|
162
|
-
|
163
|
-
def train(args):
|
164
|
-
|
165
|
-
|
166
|
-
|
167
|
-
batchsize = args.batchsize # minibatch size
|
168
|
-
|
169
|
-
n_epoch = args.epoch # エポック数
|
170
|
-
|
171
|
-
|
172
|
-
|
173
|
-
height = 100
|
174
|
-
|
175
|
-
width = 200
|
176
|
-
|
177
|
-
|
178
|
-
|
179
|
-
#訓練データの読み込み
|
180
|
-
|
181
|
-
x_train = np.load('posneg_train_data.npy')
|
182
|
-
|
183
|
-
y_train = np.load('posneg_train_label.npy')
|
184
|
-
|
185
|
-
|
186
|
-
|
187
|
-
#テストデータの読み込み
|
188
|
-
|
189
|
-
x_test = np.load('posneg_test_data.npy')
|
190
|
-
|
191
|
-
y_test = np.load('posneg_test_label.npy')
|
192
|
-
|
193
|
-
|
194
|
-
|
195
|
-
N_test = y_test.size # test data size
|
196
|
-
|
197
|
-
N = len(x_train) # train data size
|
198
|
-
|
199
|
-
in_units = x_train.shape[1] # 入力層のユニット数 (語彙数)
|
200
|
-
|
201
|
-
|
202
|
-
|
203
|
-
# (nsample, channel, height, width) の4次元テンソルに変換
|
204
|
-
|
205
|
-
input_channel = 1
|
206
|
-
|
207
|
-
x_train = x_train.reshape(len(x_train), input_channel, height, width)
|
208
|
-
|
209
|
-
x_test = x_test.reshape(len(x_test), input_channel, height, width)
|
210
|
-
|
211
|
-
|
212
|
-
|
213
|
-
n_label = 2 # ラベル数
|
214
|
-
|
215
|
-
filter_height = [3,4,5] # フィルタの高さ
|
216
|
-
|
217
|
-
baseline_filter_height = [3]
|
218
|
-
|
219
|
-
filter_width = width # フィルタの幅 (embeddingの次元数)
|
220
|
-
|
221
|
-
output_channel = 100
|
222
|
-
|
223
|
-
decay = 0.0001 # 重み減衰
|
224
|
-
|
225
|
-
grad_clip = 3 # gradient norm threshold to clip
|
226
|
-
|
227
|
-
max_sentence_len = height # max length of sentences
|
228
|
-
|
229
|
-
|
230
|
-
|
231
|
-
# モデルの定義
|
232
|
-
|
233
|
-
if args.baseline == False:
|
234
|
-
|
235
|
-
# 提案モデル
|
236
|
-
|
237
|
-
model = CNNSC(input_channel,
|
238
|
-
|
239
|
-
output_channel,
|
240
|
-
|
241
|
-
filter_height,
|
242
|
-
|
243
|
-
filter_width,
|
244
|
-
|
245
|
-
n_label,
|
246
|
-
|
247
|
-
max_sentence_len)
|
248
|
-
|
249
|
-
else:
|
250
|
-
|
251
|
-
# ベースラインモデル (フィルタの種類が1つ)
|
252
|
-
|
253
|
-
model = CNNSC(input_channel,
|
254
|
-
|
255
|
-
output_channel,
|
256
|
-
|
257
|
-
baseline_filter_height,
|
258
|
-
|
259
|
-
filter_width,
|
260
|
-
|
261
|
-
n_label,
|
262
|
-
|
263
|
-
max_sentence_len)
|
264
|
-
|
265
|
-
|
266
|
-
|
267
|
-
# Setup optimizer
|
268
|
-
|
269
|
-
optimizer = optimizers.AdaDelta()
|
270
|
-
|
271
|
-
optimizer.setup(model)
|
272
|
-
|
273
|
-
optimizer.add_hook(chainer.optimizer.GradientClipping(grad_clip))
|
274
|
-
|
275
|
-
optimizer.add_hook(chainer.optimizer.WeightDecay(decay))
|
276
|
-
|
277
|
-
|
278
|
-
|
279
|
-
#GPUを使うかどうか
|
280
|
-
|
281
|
-
if args.gpu >= 0:
|
282
|
-
|
283
|
-
cuda.check_cuda_available()
|
284
|
-
|
285
|
-
cuda.get_device(args.gpu).use()
|
286
|
-
|
287
|
-
model.to_gpu()
|
288
|
-
|
289
|
-
xp = np if args.gpu < 0 else cuda.cupy #args.gpu <= 0: use cpu, otherwise: use gpu
|
290
|
-
|
291
|
-
|
292
|
-
|
293
|
-
# Learning loop
|
294
|
-
|
295
|
-
for epoch in six.moves.range(1, n_epoch + 1):
|
296
|
-
|
297
|
-
|
298
|
-
|
299
|
-
print ('epoch', epoch, '/', n_epoch)
|
300
|
-
|
301
|
-
|
302
|
-
|
303
|
-
# training
|
304
|
-
|
305
|
-
perm = np.random.permutation(N) #ランダムな整数列リストを取得
|
306
|
-
|
307
|
-
sum_train_loss = 0.0
|
308
|
-
|
309
|
-
sum_train_accuracy = 0.0
|
310
|
-
|
311
|
-
for i in six.moves.range(0, N, batchsize):
|
312
|
-
|
313
|
-
|
314
|
-
|
315
|
-
#perm を使い x_train, y_trainからデータセットを選択 (毎回対象となるデータは異なる)
|
316
|
-
|
317
|
-
x = chainer.Variable(xp.asarray(x_train[perm[i:i + batchsize]])) #source
|
318
|
-
|
319
|
-
t = chainer.Variable(xp.asarray(y_train[perm[i:i + batchsize]])) #target
|
320
|
-
|
321
|
-
|
322
|
-
|
323
|
-
model.zerograds()
|
324
|
-
|
325
|
-
|
326
|
-
|
327
|
-
y = model(x)
|
328
|
-
|
329
|
-
loss = F.softmax_cross_entropy(y, t) # 損失の計算
|
330
|
-
|
331
|
-
accuracy = F.accuracy(y, t) # 正解率の計算
|
332
|
-
|
333
|
-
|
334
|
-
|
335
|
-
sum_train_loss += loss.data * len(t)
|
336
|
-
|
337
|
-
sum_train_accuracy += accuracy.data * len(t)
|
338
|
-
|
339
|
-
|
340
|
-
|
341
|
-
# 最適化を実行
|
342
|
-
|
343
|
-
loss.backward()
|
344
|
-
|
345
|
-
optimizer.update()
|
346
|
-
|
347
|
-
|
348
|
-
|
349
|
-
print('train mean loss={}, accuracy={}'.format(sum_train_loss / N, sum_train_accuracy / N)) #平均誤差
|
350
|
-
|
351
|
-
|
352
|
-
|
353
|
-
# evaluation
|
354
|
-
|
355
|
-
sum_test_loss = 0.0
|
356
|
-
|
357
|
-
sum_test_accuracy = 0.0
|
358
|
-
|
359
|
-
for i in six.moves.range(0, N_test, batchsize):
|
360
|
-
|
361
|
-
|
362
|
-
|
363
|
-
# all test data
|
364
|
-
|
365
|
-
x = chainer.Variable(xp.asarray(x_test[i:i + batchsize]))
|
366
|
-
|
367
|
-
t = chainer.Variable(xp.asarray(y_test[i:i + batchsize]))
|
368
|
-
|
369
|
-
|
370
|
-
|
371
|
-
y = model(x, False)
|
372
|
-
|
373
|
-
loss = F.softmax_cross_entropy(y, t) # 損失の計算
|
374
|
-
|
375
|
-
accuracy = F.accuracy(y, t) # 正解率の計算
|
376
|
-
|
377
|
-
|
378
|
-
|
379
|
-
sum_test_loss += loss.data * len(t)
|
380
|
-
|
381
|
-
sum_test_accuracy += accuracy.data * len(t)
|
382
|
-
|
383
|
-
|
384
|
-
|
385
|
-
print(' test mean loss={}, accuracy={}'.format(sum_test_loss / N_test, sum_test_accuracy / N_test)) #平均誤差
|
386
|
-
|
387
|
-
|
388
|
-
|
389
|
-
sys.stdout.flush()
|
390
|
-
|
391
|
-
|
392
|
-
|
393
|
-
return model, optimizer
|
394
|
-
|
395
|
-
|
396
|
-
|
397
|
-
def main():
|
398
|
-
|
399
|
-
parser = get_parser()
|
400
|
-
|
401
|
-
args = parser.parse_args()
|
423
|
+
(base) C:\jikken>python confirm.py --save-model C:/jikken --save-optimizer C:/jikken
|
424
|
+
|
425
|
+
epoch 1 / 100
|
426
|
+
|
427
|
+
Traceback (most recent call last):
|
428
|
+
|
429
|
+
File "confirm.py", line 202, in <module>
|
430
|
+
|
431
|
+
main()
|
432
|
+
|
433
|
+
File "confirm.py", line 194, in main
|
402
434
|
|
403
435
|
model, optimizer = train(args)
|
404
436
|
|
405
|
-
|
406
|
-
|
407
|
-
|
437
|
+
File "confirm.py", line 156, in train
|
408
|
-
|
438
|
+
|
409
|
-
|
439
|
+
y = model(x)
|
410
|
-
|
440
|
+
|
411
|
-
|
441
|
+
File "C:\jikken\CNNSC.py", line 56, in __call__
|
442
|
+
|
412
|
-
|
443
|
+
h_l1 = F.dropout(F.tanh(self[self.cnv_num+0](concat)), ratio=0.5, train=train)
|
444
|
+
|
445
|
+
File "C:\Anaconda\lib\site-packages\chainer\functions\noise\dropout.py", line 163, in dropout
|
446
|
+
|
447
|
+
kwargs, train='train argument is not supported anymore. '
|
448
|
+
|
449
|
+
File "C:\Anaconda\lib\site-packages\chainer\utils\argument.py", line 7, in check_unexpected_kwargs
|
450
|
+
|
413
|
-
|
451
|
+
raise ValueError(message)
|
414
|
-
|
415
|
-
|
416
|
-
|
452
|
+
|
417
|
-
i
|
453
|
+
ValueError: train argument is not supported anymore. Use chainer.using_config
|
418
|
-
|
419
|
-
main()
|
420
|
-
|
421
|
-
|
422
454
|
|
423
455
|
```
|
424
456
|
|
425
457
|
|
426
458
|
|
427
|
-
#エラーメッセージ
|
428
|
-
|
429
|
-
```
|
430
|
-
|
431
|
-
(base) C:\jikken>python confirm.py --save-model C:/jikken --save-optimizer C:/jikken
|
432
|
-
|
433
|
-
epoch 1 / 100
|
434
|
-
|
435
|
-
Traceback (most recent call last):
|
436
|
-
|
437
|
-
File "confirm.py", line 202, in <module>
|
438
|
-
|
439
|
-
main()
|
440
|
-
|
441
|
-
File "confirm.py", line 194, in main
|
442
|
-
|
443
|
-
model, optimizer = train(args)
|
444
|
-
|
445
|
-
File "confirm.py", line 156, in train
|
446
|
-
|
447
|
-
y = model(x)
|
448
|
-
|
449
|
-
File "C:\jikken\CNNSC.py", line 50, in __call__
|
450
|
-
|
451
|
-
h_conv[i] = F.relu(self[i](x))
|
452
|
-
|
453
|
-
File "C:\Anaconda\lib\site-packages\chainer\links\connection\convolution_2d.py", line 175, in __call__
|
454
|
-
|
455
|
-
groups=self.groups)
|
456
|
-
|
457
|
-
File "C:\Anaconda\lib\site-packages\chainer\functions\connection\convolution_2d.py", line 582, in convolution_2d
|
458
|
-
|
459
|
-
y, = fnode.apply(args)
|
460
|
-
|
461
|
-
File "C:\Anaconda\lib\site-packages\chainer\function_node.py", line 243, in apply
|
462
|
-
|
463
|
-
self._check_data_type_forward(in_data)
|
464
|
-
|
465
|
-
File "C:\Anaconda\lib\site-packages\chainer\function_node.py", line 328, in _check_data_type_forward
|
466
|
-
|
467
|
-
self.check_type_forward(in_type)
|
468
|
-
|
469
|
-
File "C:\Anaconda\lib\site-packages\chainer\functions\connection\convolution_2d.py", line 68, in check_type_forward
|
470
|
-
|
471
|
-
b_type.shape[0] == w_type.shape[0],
|
472
|
-
|
473
|
-
File "C:\Anaconda\lib\site-packages\chainer\utils\type_check.py", line 524, in expect
|
474
|
-
|
475
|
-
expr.expect()
|
476
|
-
|
477
|
-
File "C:\Anaconda\lib\site-packages\chainer\utils\type_check.py", line 482, in expect
|
478
|
-
|
479
|
-
'{0} {1} {2}'.format(left, self.inv, right))
|
480
|
-
|
481
|
-
chainer.utils.type_check.InvalidType:
|
482
|
-
|
483
|
-
Invalid operation is performed in: Convolution2DFunction (Forward)
|
484
|
-
|
485
|
-
|
486
|
-
|
487
|
-
Expect: in_types[2].dtype == in_types[0].dtype
|
488
|
-
|
489
|
-
Actual: float32 != float64
|
490
|
-
|
491
|
-
```
|
492
|
-
|
493
|
-
|
494
|
-
|
495
459
|
#備考
|
496
460
|
|
497
461
|
参考にしたページはこちらです。
|
498
462
|
|
499
463
|
https://qiita.com/ichiroex/items/7ff1cff3840520cf2410
|
500
|
-
|
501
|
-
|
502
|
-
|
503
|
-
printしてみて、
|
504
|
-
|
505
|
-
```
|
506
|
-
|
507
|
-
y = model(x)
|
508
|
-
|
509
|
-
```
|
510
|
-
|
511
|
-
がErrorの原因だと分かりましたが、解消方法が分かりません。
|
1
追記
test
CHANGED
File without changes
|
test
CHANGED
@@ -497,3 +497,15 @@
|
|
497
497
|
参考にしたページはこちらです。
|
498
498
|
|
499
499
|
https://qiita.com/ichiroex/items/7ff1cff3840520cf2410
|
500
|
+
|
501
|
+
|
502
|
+
|
503
|
+
printしてみて、
|
504
|
+
|
505
|
+
```
|
506
|
+
|
507
|
+
y = model(x)
|
508
|
+
|
509
|
+
```
|
510
|
+
|
511
|
+
がErrorの原因だと分かりましたが、解消方法が分かりません。
|