-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathunet.py
97 lines (72 loc) · 4.78 KB
/
unet.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
#os.environ["CUDA_VISIBLE_DEVICES"] = "1"
import os
import numpy as np
from keras.models import *
from keras.layers import Input, merge, Conv2D, MaxPooling2D, UpSampling2D, Dropout, Cropping2D
from keras.optimizers import *
from keras.callbacks import ModelCheckpoint, LearningRateScheduler, TensorBoard
from keras import backend as keras
from generator import generate
from audio import getAudio
def get_unet(img_rows=224, img_cols=224):
inputs = Input((img_rows, img_cols,1))
audio, audio_in, _ = getAudio(img_rows, img_cols)
conv1 = Conv2D(64, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(inputs)
print ("conv1 shape:",conv1.shape)
conv1 = Conv2D(64, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv1)
print ("conv1 shape:",conv1.shape)
pool1 = MaxPooling2D(pool_size=(2, 2))(conv1)
print ("pool1 shape:",pool1.shape)
conv2 = Conv2D(128, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(pool1)
print ("conv2 shape:",conv2.shape)
conv2 = Conv2D(128, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv2)
print ("conv2 shape:",conv2.shape)
pool2 = MaxPooling2D(pool_size=(2, 2))(conv2)
print ("pool2 shape:",pool2.shape)
conv3 = Conv2D(256, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(pool2)
print ("conv3 shape:",conv3.shape)
conv3 = Conv2D(256, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv3)
print ("conv3 shape:",conv3.shape)
pool3 = MaxPooling2D(pool_size=(2, 2))(conv3)
print ("pool3 shape:",pool3.shape)
conv4 = Conv2D(512, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(pool3)
conv4 = Conv2D(512, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv4)
drop4 = Dropout(0.5)(conv4)
pool4 = MaxPooling2D(pool_size=(2, 2))(drop4)
conv5 = Conv2D(1024, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(pool4)
conv5 = Conv2D(1024, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv5)
drop5 = Dropout(0.5)(conv5)
mergeAudio = (merge([drop5, audio], mode = 'concat'))
up6 = Conv2D(512, 2, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(UpSampling2D(size = (2,2))(mergeAudio))
merge6 = merge([drop4,up6], mode = 'concat', concat_axis = 3)
conv6 = Conv2D(512, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(merge6)
conv6 = Conv2D(512, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv6)
up7 = Conv2D(256, 2, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(UpSampling2D(size = (2,2))(conv6))
merge7 = merge([conv3,up7], mode = 'concat', concat_axis = 3)
conv7 = Conv2D(256, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(merge7)
conv7 = Conv2D(256, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv7)
up8 = Conv2D(128, 2, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(UpSampling2D(size = (2,2))(conv7))
merge8 = merge([conv2,up8], mode = 'concat', concat_axis = 3)
conv8 = Conv2D(128, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(merge8)
conv8 = Conv2D(128, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv8)
up9 = Conv2D(64, 2, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(UpSampling2D(size = (2,2))(conv8))
merge9 = merge([conv1,up9], mode = 'concat', concat_axis = 3)
conv9 = Conv2D(64, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(merge9)
conv9 = Conv2D(64, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv9)
conv9 = Conv2D(2, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv9)
conv10 = Conv2D(1, 1, activation = 'sigmoid')(conv9)
print('here')
model = Model(input = [inputs, audio_in], output = conv10)
model.compile(optimizer = Adam(lr = 1e-4), loss = 'MSE', metrics = ['accuracy'])
return model
def train():
TensorBoard(log_dir='./Graph', histogram_freq=0,
write_graph=True, write_images=True)
tbCallBack = TensorBoard(log_dir='./Graph', histogram_freq=0, write_graph=True, write_images=True)
model = get_unet()
print("got unet")
model_checkpoint = ModelCheckpoint('ynet.hdf5', monitor='loss', save_best_only=False, verbose=1, mode='auto', period=10)
print('Fitting model...')
model.fit_generator(generate(100, 12), steps_per_epoch=20, epochs=2000, verbose=1, callbacks=[model_checkpoint, tbCallBack])
if __name__ == '__main__':
train()