-
Notifications
You must be signed in to change notification settings - Fork 109
/
DRSN_TFLearn.py
146 lines (116 loc) · 5.87 KB
/
DRSN_TFLearn.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
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Mon Dec 23 21:23:09 2019
Implemented using TensorFlow 1.0 and TFLearn 0.3.2
M. Zhao, S. Zhong, X. Fu, B. Tang, M. Pecht, Deep Residual Shrinkage Networks for Fault Diagnosis,
IEEE Transactions on Industrial Informatics, 2019, DOI: 10.1109/TII.2019.2943898
@author: super_9527
"""
from __future__ import division, print_function, absolute_import
import tflearn
import numpy as np
import tensorflow as tf
from tflearn.layers.conv import conv_2d
# Data loading
from tflearn.datasets import cifar10
(X, Y), (testX, testY) = cifar10.load_data()
# Add noise
X = X + np.random.random((50000, 32, 32, 3))*0.1
testX = testX + np.random.random((10000, 32, 32, 3))*0.1
# Transform labels to one-hot format
Y = tflearn.data_utils.to_categorical(Y,10)
testY = tflearn.data_utils.to_categorical(testY,10)
def residual_shrinkage_block(incoming, nb_blocks, out_channels, downsample=False,
downsample_strides=2, activation='relu', batch_norm=True,
bias=True, weights_init='variance_scaling',
bias_init='zeros', regularizer='L2', weight_decay=0.0001,
trainable=True, restore=True, reuse=False, scope=None,
name="ResidualBlock"):
# residual shrinkage blocks with channel-wise thresholds
residual = incoming
in_channels = incoming.get_shape().as_list()[-1]
# Variable Scope fix for older TF
try:
vscope = tf.variable_scope(scope, default_name=name, values=[incoming],
reuse=reuse)
except Exception:
vscope = tf.variable_op_scope([incoming], scope, name, reuse=reuse)
with vscope as scope:
name = scope.name #TODO
for i in range(nb_blocks):
identity = residual
if not downsample:
downsample_strides = 1
if batch_norm:
residual = tflearn.batch_normalization(residual)
residual = tflearn.activation(residual, activation)
residual = conv_2d(residual, out_channels, 3,
downsample_strides, 'same', 'linear',
bias, weights_init, bias_init,
regularizer, weight_decay, trainable,
restore)
if batch_norm:
residual = tflearn.batch_normalization(residual)
residual = tflearn.activation(residual, activation)
residual = conv_2d(residual, out_channels, 3, 1, 'same',
'linear', bias, weights_init,
bias_init, regularizer, weight_decay,
trainable, restore)
# get thresholds and apply thresholding
abs_mean = tf.reduce_mean(tf.reduce_mean(tf.abs(residual),axis=2,keep_dims=True),axis=1,keep_dims=True)
scales = tflearn.fully_connected(abs_mean, out_channels//4, activation='linear',regularizer='L2',weight_decay=0.0001,weights_init='variance_scaling')
scales = tflearn.batch_normalization(scales)
scales = tflearn.activation(scales, 'relu')
scales = tflearn.fully_connected(scales, out_channels, activation='linear',regularizer='L2',weight_decay=0.0001,weights_init='variance_scaling')
scales = tf.expand_dims(tf.expand_dims(scales,axis=1),axis=1)
thres = tf.multiply(abs_mean,tflearn.activations.sigmoid(scales))
# soft thresholding
residual = tf.multiply(tf.sign(residual), tf.maximum(tf.abs(residual)-thres,0))
# Downsampling
if downsample_strides > 1:
identity = tflearn.avg_pool_2d(identity, 1,
downsample_strides)
# Projection to new dimension
if in_channels != out_channels:
if (out_channels - in_channels) % 2 == 0:
ch = (out_channels - in_channels)//2
identity = tf.pad(identity,
[[0, 0], [0, 0], [0, 0], [ch, ch]])
else:
ch = (out_channels - in_channels)//2
identity = tf.pad(identity,
[[0, 0], [0, 0], [0, 0], [ch, ch+1]])
in_channels = out_channels
residual = residual + identity
return residual
# Real-time data preprocessing
img_prep = tflearn.ImagePreprocessing()
img_prep.add_featurewise_zero_center(per_channel=True)
# Real-time data augmentation
img_aug = tflearn.ImageAugmentation()
img_aug.add_random_flip_leftright()
img_aug.add_random_crop([32, 32], padding=4)
# Build a Deep Residual Shrinkage Network with 3 blocks
net = tflearn.input_data(shape=[None, 32, 32, 3],
data_preprocessing=img_prep,
data_augmentation=img_aug)
net = tflearn.conv_2d(net, 16, 3, regularizer='L2', weight_decay=0.0001)
net = residual_shrinkage_block(net, 1, 16)
net = residual_shrinkage_block(net, 1, 32, downsample=True)
net = residual_shrinkage_block(net, 1, 32, downsample=True)
net = tflearn.batch_normalization(net)
net = tflearn.activation(net, 'relu')
net = tflearn.global_avg_pool(net)
# Regression
net = tflearn.fully_connected(net, 10, activation='softmax')
mom = tflearn.Momentum(0.1, lr_decay=0.1, decay_step=20000, staircase=True)
net = tflearn.regression(net, optimizer=mom, loss='categorical_crossentropy')
# Training
model = tflearn.DNN(net, checkpoint_path='model_cifar10',
max_checkpoints=10, tensorboard_verbose=0,
clip_gradients=0.)
model.fit(X, Y, n_epoch=100, snapshot_epoch=False, snapshot_step=500,
show_metric=True, batch_size=100, shuffle=True, run_id='model_cifar10')
training_acc = model.evaluate(X, Y)[0]
validation_acc = model.evaluate(testX, testY)[0]