-
-
Notifications
You must be signed in to change notification settings - Fork 2
/
Copy pathgooglenet.py
291 lines (230 loc) · 20.1 KB
/
googlenet.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
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
# -*- coding: utf-8 -*-
from keras.optimizers import SGD
from keras.layers import Input, Dense, Convolution2D, MaxPooling2D, AveragePooling2D, ZeroPadding2D, Dropout, Flatten, merge, Reshape, Activation
#from keras.datasets import cifar10
from keras.regularizers import l2
from keras.models import Model
from sklearn.metrics import log_loss
from custom_layers.googlenet_custom_layers import LRN, PoolHelper
#from load_cifar10 import load_cifar10_data
from keras.optimizers import SGD
from keras.layers import Input, merge, ZeroPadding2D
from keras.layers.core import Dense, Dropout, Activation
from keras.layers.convolutional import Convolution2D
from keras.layers.pooling import AveragePooling2D, GlobalAveragePooling2D, MaxPooling2D
from keras.layers.normalization import BatchNormalization
from keras.models import Model
import keras.backend as K
from sklearn.model_selection import train_test_split
from sklearn.metrics import log_loss
import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
import keras
from keras.applications.vgg19 import VGG19
from keras.models import Model
from keras.layers import Dense, Dropout, Flatten
import os
from tqdm import tqdm
from sklearn import preprocessing
from sklearn.model_selection import train_test_split
import cv2
from custom_layers.scale_layer import Scale
from subprocess import check_output
weight_path = '/home/sahand/MEGAsync/Projects/cnn_weights/' #weigh directory
directory_path = "/home/sahand/Desktop/dogbreed/" #data directory
def googlenet_model(img_rows, img_cols, channel=1, num_classes=None):
"""
GoogLeNet a.k.a. Inception v1 for Keras
Model Schema is based on
https://gist.github.com/joelouismarino/a2ede9ab3928f999575423b9887abd14
ImageNet Pretrained Weights
https://drive.google.com/open?id=0B319laiAPjU3RE1maU9MMlh2dnc
Blog Post:
http://joelouismarino.github.io/blog_posts/blog_googlenet_keras.html
Parameters:
img_rows, img_cols - resolution of inputs
channel - 1 for grayscale, 3 for color
num_classes - number of class labels for our classification task
"""
input = Input(shape=(channel, img_rows, img_cols))
conv1_7x7_s2 = Convolution2D(64,7,7,subsample=(2,2),border_mode='same',activation='relu',name='conv1/7x7_s2',W_regularizer=l2(0.0002))(input)
conv1_zero_pad = ZeroPadding2D(padding=(1, 1))(conv1_7x7_s2)
pool1_helper = PoolHelper()(conv1_zero_pad)
pool1_3x3_s2 = MaxPooling2D(pool_size=(3,3),strides=(2,2),border_mode='valid',name='pool1/3x3_s2')(pool1_helper)
pool1_norm1 = LRN(name='pool1/norm1')(pool1_3x3_s2)
conv2_3x3_reduce = Convolution2D(64,1,1,border_mode='same',activation='relu',name='conv2/3x3_reduce',W_regularizer=l2(0.0002))(pool1_norm1)
conv2_3x3 = Convolution2D(192,3,3,border_mode='same',activation='relu',name='conv2/3x3',W_regularizer=l2(0.0002))(conv2_3x3_reduce)
conv2_norm2 = LRN(name='conv2/norm2')(conv2_3x3)
conv2_zero_pad = ZeroPadding2D(padding=(1, 1))(conv2_norm2)
pool2_helper = PoolHelper()(conv2_zero_pad)
pool2_3x3_s2 = MaxPooling2D(pool_size=(3,3),strides=(2,2),border_mode='valid',name='pool2/3x3_s2')(pool2_helper)
inception_3a_1x1 = Convolution2D(64,1,1,border_mode='same',activation='relu',name='inception_3a/1x1',W_regularizer=l2(0.0002))(pool2_3x3_s2)
inception_3a_3x3_reduce = Convolution2D(96,1,1,border_mode='same',activation='relu',name='inception_3a/3x3_reduce',W_regularizer=l2(0.0002))(pool2_3x3_s2)
inception_3a_3x3 = Convolution2D(128,3,3,border_mode='same',activation='relu',name='inception_3a/3x3',W_regularizer=l2(0.0002))(inception_3a_3x3_reduce)
inception_3a_5x5_reduce = Convolution2D(16,1,1,border_mode='same',activation='relu',name='inception_3a/5x5_reduce',W_regularizer=l2(0.0002))(pool2_3x3_s2)
inception_3a_5x5 = Convolution2D(32,5,5,border_mode='same',activation='relu',name='inception_3a/5x5',W_regularizer=l2(0.0002))(inception_3a_5x5_reduce)
inception_3a_pool = MaxPooling2D(pool_size=(3,3),strides=(1,1),border_mode='same',name='inception_3a/pool')(pool2_3x3_s2)
inception_3a_pool_proj = Convolution2D(32,1,1,border_mode='same',activation='relu',name='inception_3a/pool_proj',W_regularizer=l2(0.0002))(inception_3a_pool)
inception_3a_output = merge([inception_3a_1x1,inception_3a_3x3,inception_3a_5x5,inception_3a_pool_proj],mode='concat',concat_axis=1,name='inception_3a/output')
inception_3b_1x1 = Convolution2D(128,1,1,border_mode='same',activation='relu',name='inception_3b/1x1',W_regularizer=l2(0.0002))(inception_3a_output)
inception_3b_3x3_reduce = Convolution2D(128,1,1,border_mode='same',activation='relu',name='inception_3b/3x3_reduce',W_regularizer=l2(0.0002))(inception_3a_output)
inception_3b_3x3 = Convolution2D(192,3,3,border_mode='same',activation='relu',name='inception_3b/3x3',W_regularizer=l2(0.0002))(inception_3b_3x3_reduce)
inception_3b_5x5_reduce = Convolution2D(32,1,1,border_mode='same',activation='relu',name='inception_3b/5x5_reduce',W_regularizer=l2(0.0002))(inception_3a_output)
inception_3b_5x5 = Convolution2D(96,5,5,border_mode='same',activation='relu',name='inception_3b/5x5',W_regularizer=l2(0.0002))(inception_3b_5x5_reduce)
inception_3b_pool = MaxPooling2D(pool_size=(3,3),strides=(1,1),border_mode='same',name='inception_3b/pool')(inception_3a_output)
inception_3b_pool_proj = Convolution2D(64,1,1,border_mode='same',activation='relu',name='inception_3b/pool_proj',W_regularizer=l2(0.0002))(inception_3b_pool)
inception_3b_output = merge([inception_3b_1x1,inception_3b_3x3,inception_3b_5x5,inception_3b_pool_proj],mode='concat',concat_axis=1,name='inception_3b/output')
inception_3b_output_zero_pad = ZeroPadding2D(padding=(1, 1))(inception_3b_output)
pool3_helper = PoolHelper()(inception_3b_output_zero_pad)
pool3_3x3_s2 = MaxPooling2D(pool_size=(3,3),strides=(2,2),border_mode='valid',name='pool3/3x3_s2')(pool3_helper)
inception_4a_1x1 = Convolution2D(192,1,1,border_mode='same',activation='relu',name='inception_4a/1x1',W_regularizer=l2(0.0002))(pool3_3x3_s2)
inception_4a_3x3_reduce = Convolution2D(96,1,1,border_mode='same',activation='relu',name='inception_4a/3x3_reduce',W_regularizer=l2(0.0002))(pool3_3x3_s2)
inception_4a_3x3 = Convolution2D(208,3,3,border_mode='same',activation='relu',name='inception_4a/3x3',W_regularizer=l2(0.0002))(inception_4a_3x3_reduce)
inception_4a_5x5_reduce = Convolution2D(16,1,1,border_mode='same',activation='relu',name='inception_4a/5x5_reduce',W_regularizer=l2(0.0002))(pool3_3x3_s2)
inception_4a_5x5 = Convolution2D(48,5,5,border_mode='same',activation='relu',name='inception_4a/5x5',W_regularizer=l2(0.0002))(inception_4a_5x5_reduce)
inception_4a_pool = MaxPooling2D(pool_size=(3,3),strides=(1,1),border_mode='same',name='inception_4a/pool')(pool3_3x3_s2)
inception_4a_pool_proj = Convolution2D(64,1,1,border_mode='same',activation='relu',name='inception_4a/pool_proj',W_regularizer=l2(0.0002))(inception_4a_pool)
inception_4a_output = merge([inception_4a_1x1,inception_4a_3x3,inception_4a_5x5,inception_4a_pool_proj],mode='concat',concat_axis=1,name='inception_4a/output')
loss1_ave_pool = AveragePooling2D(pool_size=(5,5),strides=(3,3),name='loss1/ave_pool')(inception_4a_output)
loss1_conv = Convolution2D(128,1,1,border_mode='same',activation='relu',name='loss1/conv',W_regularizer=l2(0.0002))(loss1_ave_pool)
loss1_flat = Flatten()(loss1_conv)
loss1_fc = Dense(1024,activation='relu',name='loss1/fc',W_regularizer=l2(0.0002))(loss1_flat)
loss1_drop_fc = Dropout(0.7)(loss1_fc)
loss1_classifier = Dense(1000,name='loss1/classifier',W_regularizer=l2(0.0002))(loss1_drop_fc)
loss1_classifier_act = Activation('softmax')(loss1_classifier)
inception_4b_1x1 = Convolution2D(160,1,1,border_mode='same',activation='relu',name='inception_4b/1x1',W_regularizer=l2(0.0002))(inception_4a_output)
inception_4b_3x3_reduce = Convolution2D(112,1,1,border_mode='same',activation='relu',name='inception_4b/3x3_reduce',W_regularizer=l2(0.0002))(inception_4a_output)
inception_4b_3x3 = Convolution2D(224,3,3,border_mode='same',activation='relu',name='inception_4b/3x3',W_regularizer=l2(0.0002))(inception_4b_3x3_reduce)
inception_4b_5x5_reduce = Convolution2D(24,1,1,border_mode='same',activation='relu',name='inception_4b/5x5_reduce',W_regularizer=l2(0.0002))(inception_4a_output)
inception_4b_5x5 = Convolution2D(64,5,5,border_mode='same',activation='relu',name='inception_4b/5x5',W_regularizer=l2(0.0002))(inception_4b_5x5_reduce)
inception_4b_pool = MaxPooling2D(pool_size=(3,3),strides=(1,1),border_mode='same',name='inception_4b/pool')(inception_4a_output)
inception_4b_pool_proj = Convolution2D(64,1,1,border_mode='same',activation='relu',name='inception_4b/pool_proj',W_regularizer=l2(0.0002))(inception_4b_pool)
inception_4b_output = merge([inception_4b_1x1,inception_4b_3x3,inception_4b_5x5,inception_4b_pool_proj],mode='concat',concat_axis=1,name='inception_4b_output')
inception_4c_1x1 = Convolution2D(128,1,1,border_mode='same',activation='relu',name='inception_4c/1x1',W_regularizer=l2(0.0002))(inception_4b_output)
inception_4c_3x3_reduce = Convolution2D(128,1,1,border_mode='same',activation='relu',name='inception_4c/3x3_reduce',W_regularizer=l2(0.0002))(inception_4b_output)
inception_4c_3x3 = Convolution2D(256,3,3,border_mode='same',activation='relu',name='inception_4c/3x3',W_regularizer=l2(0.0002))(inception_4c_3x3_reduce)
inception_4c_5x5_reduce = Convolution2D(24,1,1,border_mode='same',activation='relu',name='inception_4c/5x5_reduce',W_regularizer=l2(0.0002))(inception_4b_output)
inception_4c_5x5 = Convolution2D(64,5,5,border_mode='same',activation='relu',name='inception_4c/5x5',W_regularizer=l2(0.0002))(inception_4c_5x5_reduce)
inception_4c_pool = MaxPooling2D(pool_size=(3,3),strides=(1,1),border_mode='same',name='inception_4c/pool')(inception_4b_output)
inception_4c_pool_proj = Convolution2D(64,1,1,border_mode='same',activation='relu',name='inception_4c/pool_proj',W_regularizer=l2(0.0002))(inception_4c_pool)
inception_4c_output = merge([inception_4c_1x1,inception_4c_3x3,inception_4c_5x5,inception_4c_pool_proj],mode='concat',concat_axis=1,name='inception_4c/output')
inception_4d_1x1 = Convolution2D(112,1,1,border_mode='same',activation='relu',name='inception_4d/1x1',W_regularizer=l2(0.0002))(inception_4c_output)
inception_4d_3x3_reduce = Convolution2D(144,1,1,border_mode='same',activation='relu',name='inception_4d/3x3_reduce',W_regularizer=l2(0.0002))(inception_4c_output)
inception_4d_3x3 = Convolution2D(288,3,3,border_mode='same',activation='relu',name='inception_4d/3x3',W_regularizer=l2(0.0002))(inception_4d_3x3_reduce)
inception_4d_5x5_reduce = Convolution2D(32,1,1,border_mode='same',activation='relu',name='inception_4d/5x5_reduce',W_regularizer=l2(0.0002))(inception_4c_output)
inception_4d_5x5 = Convolution2D(64,5,5,border_mode='same',activation='relu',name='inception_4d/5x5',W_regularizer=l2(0.0002))(inception_4d_5x5_reduce)
inception_4d_pool = MaxPooling2D(pool_size=(3,3),strides=(1,1),border_mode='same',name='inception_4d/pool')(inception_4c_output)
inception_4d_pool_proj = Convolution2D(64,1,1,border_mode='same',activation='relu',name='inception_4d/pool_proj',W_regularizer=l2(0.0002))(inception_4d_pool)
inception_4d_output = merge([inception_4d_1x1,inception_4d_3x3,inception_4d_5x5,inception_4d_pool_proj],mode='concat',concat_axis=1,name='inception_4d/output')
loss2_ave_pool = AveragePooling2D(pool_size=(5,5),strides=(3,3),name='loss2/ave_pool')(inception_4d_output)
loss2_conv = Convolution2D(128,1,1,border_mode='same',activation='relu',name='loss2/conv',W_regularizer=l2(0.0002))(loss2_ave_pool)
loss2_flat = Flatten()(loss2_conv)
loss2_fc = Dense(1024,activation='relu',name='loss2/fc',W_regularizer=l2(0.0002))(loss2_flat)
loss2_drop_fc = Dropout(0.7)(loss2_fc)
loss2_classifier = Dense(1000,name='loss2/classifier',W_regularizer=l2(0.0002))(loss2_drop_fc)
loss2_classifier_act = Activation('softmax')(loss2_classifier)
inception_4e_1x1 = Convolution2D(256,1,1,border_mode='same',activation='relu',name='inception_4e/1x1',W_regularizer=l2(0.0002))(inception_4d_output)
inception_4e_3x3_reduce = Convolution2D(160,1,1,border_mode='same',activation='relu',name='inception_4e/3x3_reduce',W_regularizer=l2(0.0002))(inception_4d_output)
inception_4e_3x3 = Convolution2D(320,3,3,border_mode='same',activation='relu',name='inception_4e/3x3',W_regularizer=l2(0.0002))(inception_4e_3x3_reduce)
inception_4e_5x5_reduce = Convolution2D(32,1,1,border_mode='same',activation='relu',name='inception_4e/5x5_reduce',W_regularizer=l2(0.0002))(inception_4d_output)
inception_4e_5x5 = Convolution2D(128,5,5,border_mode='same',activation='relu',name='inception_4e/5x5',W_regularizer=l2(0.0002))(inception_4e_5x5_reduce)
inception_4e_pool = MaxPooling2D(pool_size=(3,3),strides=(1,1),border_mode='same',name='inception_4e/pool')(inception_4d_output)
inception_4e_pool_proj = Convolution2D(128,1,1,border_mode='same',activation='relu',name='inception_4e/pool_proj',W_regularizer=l2(0.0002))(inception_4e_pool)
inception_4e_output = merge([inception_4e_1x1,inception_4e_3x3,inception_4e_5x5,inception_4e_pool_proj],mode='concat',concat_axis=1,name='inception_4e/output')
inception_4e_output_zero_pad = ZeroPadding2D(padding=(1, 1))(inception_4e_output)
pool4_helper = PoolHelper()(inception_4e_output_zero_pad)
pool4_3x3_s2 = MaxPooling2D(pool_size=(3,3),strides=(2,2),border_mode='valid',name='pool4/3x3_s2')(pool4_helper)
inception_5a_1x1 = Convolution2D(256,1,1,border_mode='same',activation='relu',name='inception_5a/1x1',W_regularizer=l2(0.0002))(pool4_3x3_s2)
inception_5a_3x3_reduce = Convolution2D(160,1,1,border_mode='same',activation='relu',name='inception_5a/3x3_reduce',W_regularizer=l2(0.0002))(pool4_3x3_s2)
inception_5a_3x3 = Convolution2D(320,3,3,border_mode='same',activation='relu',name='inception_5a/3x3',W_regularizer=l2(0.0002))(inception_5a_3x3_reduce)
inception_5a_5x5_reduce = Convolution2D(32,1,1,border_mode='same',activation='relu',name='inception_5a/5x5_reduce',W_regularizer=l2(0.0002))(pool4_3x3_s2)
inception_5a_5x5 = Convolution2D(128,5,5,border_mode='same',activation='relu',name='inception_5a/5x5',W_regularizer=l2(0.0002))(inception_5a_5x5_reduce)
inception_5a_pool = MaxPooling2D(pool_size=(3,3),strides=(1,1),border_mode='same',name='inception_5a/pool')(pool4_3x3_s2)
inception_5a_pool_proj = Convolution2D(128,1,1,border_mode='same',activation='relu',name='inception_5a/pool_proj',W_regularizer=l2(0.0002))(inception_5a_pool)
inception_5a_output = merge([inception_5a_1x1,inception_5a_3x3,inception_5a_5x5,inception_5a_pool_proj],mode='concat',concat_axis=1,name='inception_5a/output')
inception_5b_1x1 = Convolution2D(384,1,1,border_mode='same',activation='relu',name='inception_5b/1x1',W_regularizer=l2(0.0002))(inception_5a_output)
inception_5b_3x3_reduce = Convolution2D(192,1,1,border_mode='same',activation='relu',name='inception_5b/3x3_reduce',W_regularizer=l2(0.0002))(inception_5a_output)
inception_5b_3x3 = Convolution2D(384,3,3,border_mode='same',activation='relu',name='inception_5b/3x3',W_regularizer=l2(0.0002))(inception_5b_3x3_reduce)
inception_5b_5x5_reduce = Convolution2D(48,1,1,border_mode='same',activation='relu',name='inception_5b/5x5_reduce',W_regularizer=l2(0.0002))(inception_5a_output)
inception_5b_5x5 = Convolution2D(128,5,5,border_mode='same',activation='relu',name='inception_5b/5x5',W_regularizer=l2(0.0002))(inception_5b_5x5_reduce)
inception_5b_pool = MaxPooling2D(pool_size=(3,3),strides=(1,1),border_mode='same',name='inception_5b/pool')(inception_5a_output)
inception_5b_pool_proj = Convolution2D(128,1,1,border_mode='same',activation='relu',name='inception_5b/pool_proj',W_regularizer=l2(0.0002))(inception_5b_pool)
inception_5b_output = merge([inception_5b_1x1,inception_5b_3x3,inception_5b_5x5,inception_5b_pool_proj],mode='concat',concat_axis=1,name='inception_5b/output')
pool5_7x7_s1 = AveragePooling2D(pool_size=(7,7),strides=(1,1),name='pool5/7x7_s2')(inception_5b_output)
loss3_flat = Flatten()(pool5_7x7_s1)
pool5_drop_7x7_s1 = Dropout(0.4)(loss3_flat)
loss3_classifier = Dense(1000,name='loss3/classifier',W_regularizer=l2(0.0002))(pool5_drop_7x7_s1)
loss3_classifier_act = Activation('softmax',name='prob')(loss3_classifier)
# Create model
model = Model(input=input, output=[loss1_classifier_act,loss2_classifier_act,loss3_classifier_act])
# Load ImageNet pre-trained data
model.load_weights(weight_path+'googlenet_weights.h5')
# Truncate and replace softmax layer for transfer learning
# Cannot use model.layers.pop() since model is not of Sequential() type
# The method below works since pre-trained weights are stored in layers but not in the model
loss3_classifier_statefarm = Dense(num_classes,name='loss3/classifier',W_regularizer=l2(0.0002))(pool5_drop_7x7_s1)
loss3_classifier_act_statefarm = Activation('softmax',name='prob')(loss3_classifier_statefarm)
loss2_classifier_statefarm = Dense(num_classes,name='loss2/classifier',W_regularizer=l2(0.0002))(loss2_drop_fc)
loss2_classifier_act_statefarm = Activation('softmax')(loss2_classifier_statefarm)
loss1_classifier_statefarm = Dense(num_classes,name='loss1/classifier',W_regularizer=l2(0.0002))(loss1_drop_fc)
loss1_classifier_act_statefarm = Activation('softmax')(loss1_classifier_statefarm)
# Create another model with our customized softmax
model = Model(input=input, output=[loss1_classifier_act_statefarm,loss2_classifier_act_statefarm,loss3_classifier_act_statefarm])
# Learning rate is changed to 0.001
sgd = SGD(lr=1e-3, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(optimizer=sgd, loss='categorical_crossentropy', metrics=['accuracy'])
return model
if __name__ == '__main__':
# Example to fine-tune on 3000 samples from Cifar10
img_rows, img_cols = 224, 224 # Resolution of inputs
channel = 3
num_classes = 120
batch_size = 8
nb_epoch = 10
# Load Cifar10 data. Please implement your own load_data() module for your own dataset
print(check_output(["ls", directory_path]).decode("utf8"))
df_train = pd.read_csv(directory_path+'labels.csv')
df_test = pd.read_csv(directory_path+'sample_submission.csv')
targets_series = pd.Series(df_train['breed'])
one_hot = pd.get_dummies(targets_series, sparse = True)
one_hot_labels = np.asarray(one_hot)
im_size = 224
x_train = []
y_train = []
x_test = []
i = 0
for f, breed in tqdm(df_train.values):
img = cv2.imread(directory_path+'train/{}.jpg'.format(f))
label = one_hot_labels[i]
x_train.append(cv2.resize(img, (im_size, im_size)))
y_train.append(label)
i += 1
for f in tqdm(df_test['id'].values):
img = cv2.imread(directory_path+'test/{}.jpg'.format(f))
x_test.append(cv2.resize(img, (im_size, im_size)))
y_train_raw = np.array(y_train, np.uint8)
x_train_raw = np.array(x_train, np.float32) / 255.
x_test = np.array(x_test, np.float32) / 255.
print(x_train_raw.shape)
print(y_train_raw.shape)
print(x_test.shape)
num_class = y_train_raw.shape[1]
X_train, X_valid, Y_train, Y_valid = train_test_split(x_train_raw, y_train_raw, test_size=0.3, random_state=1)
#X_train, Y_train, X_valid, Y_valid = load_cifar10_data(img_rows, img_cols)
# Load our model
model = googlenet_model(img_rows, img_cols, channel, num_classes)
# Start Fine-tuning.
# Notice that googlenet takes 3 sets of labels for outputs, one for each auxillary classifier
model.fit(X_train, [Y_train, Y_train, Y_train],
batch_size=batch_size,
nb_epoch=nb_epoch,
shuffle=True,
verbose=1,
validation_data=(X_valid, [Y_valid, Y_valid, Y_valid]),
)
# Make predictions
predictions_valid = model.predict(X_valid, batch_size=batch_size, verbose=1)
# Combine 3 set of outputs using averaging
predictions_valid = sum(predictions_valid)/len(predictions_valid)
# Cross-entropy loss score
score = log_loss(Y_valid, predictions_valid)