-
Notifications
You must be signed in to change notification settings - Fork 106
/
Copy pathcifar100vgg.py
221 lines (165 loc) · 8.24 KB
/
cifar100vgg.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
from __future__ import print_function
import keras
from keras.datasets import cifar100
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Conv2D, MaxPooling2D, BatchNormalization
from keras import optimizers
import numpy as np
from keras.layers.core import Lambda
from keras import backend as K
from keras import regularizers
class cifar100vgg:
def __init__(self,train=True):
self.num_classes = 100
self.weight_decay = 0.0005
self.x_shape = [32,32,3]
self.model = self.build_model()
if train:
self.model = self.train(self.model)
else:
self.model.load_weights('cifar100vgg.h5')
def build_model(self):
# Build the network of vgg for 10 classes with massive dropout and weight decay as described in the paper.
model = Sequential()
weight_decay = self.weight_decay
model.add(Conv2D(64, (3, 3), padding='same',
input_shape=self.x_shape,kernel_regularizer=regularizers.l2(weight_decay)))
model.add(Activation('relu'))
model.add(BatchNormalization())
model.add(Dropout(0.3))
model.add(Conv2D(64, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
model.add(Activation('relu'))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(128, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
model.add(Activation('relu'))
model.add(BatchNormalization())
model.add(Dropout(0.4))
model.add(Conv2D(128, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
model.add(Activation('relu'))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(256, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
model.add(Activation('relu'))
model.add(BatchNormalization())
model.add(Dropout(0.4))
model.add(Conv2D(256, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
model.add(Activation('relu'))
model.add(BatchNormalization())
model.add(Dropout(0.4))
model.add(Conv2D(256, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
model.add(Activation('relu'))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(512, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
model.add(Activation('relu'))
model.add(BatchNormalization())
model.add(Dropout(0.4))
model.add(Conv2D(512, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
model.add(Activation('relu'))
model.add(BatchNormalization())
model.add(Dropout(0.4))
model.add(Conv2D(512, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
model.add(Activation('relu'))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(512, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
model.add(Activation('relu'))
model.add(BatchNormalization())
model.add(Dropout(0.4))
model.add(Conv2D(512, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
model.add(Activation('relu'))
model.add(BatchNormalization())
model.add(Dropout(0.4))
model.add(Conv2D(512, (3, 3), padding='same',kernel_regularizer=regularizers.l2(weight_decay)))
model.add(Activation('relu'))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.5))
model.add(Flatten())
model.add(Dense(512,kernel_regularizer=regularizers.l2(weight_decay)))
model.add(Activation('relu'))
model.add(BatchNormalization())
model.add(Dropout(0.5))
model.add(Dense(self.num_classes))
model.add(Activation('softmax'))
return model
def normalize(self,X_train,X_test):
#this function normalize inputs for zero mean and unit variance
# it is used when training a model.
# Input: training set and test set
# Output: normalized training set and test set according to the trianing set statistics.
mean = np.mean(X_train,axis=(0,1,2,3))
std = np.std(X_train, axis=(0, 1, 2, 3))
print(mean)
print(std)
X_train = (X_train-mean)/(std+1e-7)
X_test = (X_test-mean)/(std+1e-7)
return X_train, X_test
def normalize_production(self,x):
#this function is used to normalize instances in production according to saved training set statistics
# Input: X - a training set
# Output X - a normalized training set according to normalization constants.
#these values produced during first training and are general for the standard cifar10 training set normalization
mean = 121.936
std = 68.389
return (x-mean)/(std+1e-7)
def predict(self,x,normalize=True,batch_size=50):
if normalize:
x = self.normalize_production(x)
return self.model.predict(x,batch_size)
def train(self,model):
#training parameters
batch_size = 128
maxepoches = 250
learning_rate = 0.1
lr_decay = 1e-6
lr_drop = 20
# The data, shuffled and split between train and test sets:
(x_train, y_train), (x_test, y_test) = cifar100.load_data()
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train, x_test = self.normalize(x_train, x_test)
y_train = keras.utils.to_categorical(y_train, self.num_classes)
y_test = keras.utils.to_categorical(y_test, self.num_classes)
def lr_scheduler(epoch):
return learning_rate * (0.5 ** (epoch // lr_drop))
reduce_lr = keras.callbacks.LearningRateScheduler(lr_scheduler)
#data augmentation
datagen = ImageDataGenerator(
featurewise_center=False, # set input mean to 0 over the dataset
samplewise_center=False, # set each sample mean to 0
featurewise_std_normalization=False, # divide inputs by std of the dataset
samplewise_std_normalization=False, # divide each input by its std
zca_whitening=False, # apply ZCA whitening
rotation_range=15, # randomly rotate images in the range (degrees, 0 to 180)
width_shift_range=0.1, # randomly shift images horizontally (fraction of total width)
height_shift_range=0.1, # randomly shift images vertically (fraction of total height)
horizontal_flip=True, # randomly flip images
vertical_flip=False) # randomly flip images
# (std, mean, and principal components if ZCA whitening is applied).
datagen.fit(x_train)
#optimization details
sgd = optimizers.SGD(lr=learning_rate, decay=lr_decay, momentum=0.9, nesterov=True)
model.compile(loss='categorical_crossentropy', optimizer=sgd,metrics=['accuracy'])
# training process in a for loop with learning rate drop every 25 epoches.
historytemp = model.fit_generator(datagen.flow(x_train, y_train,
batch_size=batch_size),
steps_per_epoch=x_train.shape[0] // batch_size,
epochs=maxepoches,
validation_data=(x_test, y_test),callbacks=[reduce_lr],verbose=2)
model.save_weights('cifar100vgg.h5')
return model
if __name__ == '__main__':
(x_train, y_train), (x_test, y_test) = cifar100.load_data()
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
y_train = keras.utils.to_categorical(y_train, 100)
y_test = keras.utils.to_categorical(y_test, 100)
model = cifar100vgg()
predicted_x = model.predict(x_test)
residuals = (np.argmax(predicted_x,1)!=np.argmax(y_test,1))
loss = sum(residuals)/len(residuals)
print("the validation 0/1 loss is: ",loss)