forked from tensorlayer/TensorLayer
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathtutorial_vgg16.py
More file actions
183 lines (147 loc) · 8.73 KB
/
Copy pathtutorial_vgg16.py
File metadata and controls
183 lines (147 loc) · 8.73 KB
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
#! /usr/bin/python
# -*- coding: utf-8 -*-
"""
VGG-16 for ImageNet.
Introduction
----------------
VGG is a convolutional neural network model proposed by K. Simonyan and A. Zisserman
from the University of Oxford in the paper “Very Deep Convolutional Networks for
Large-Scale Image Recognition” . The model achieves 92.7% top-5 test accuracy in ImageNet,
which is a dataset of over 14 million images belonging to 1000 classes.
Download Pre-trained Model
----------------------------
- Model weights in this example - vgg16_weights.npz : http://www.cs.toronto.edu/~frossard/post/vgg16/
- Caffe VGG 16 model : https://gist.github.com/ksimonyan/211839e770f7b538e2d8#file-readme-md
- Tool to convert the Caffe models to TensorFlow's : https://github.com/ethereon/caffe-tensorflow
Note
------
- For simplified CNN layer see "Convolutional layer (Simplified)"
in read the docs website.
- When feeding other images to the model be sure to properly resize or crop them
beforehand. Distorted images might end up being misclassified. One way of safely
feeding images of multiple sizes is by doing center cropping, as shown in the
following snippet:
>>> image_h, image_w, _ = np.shape(img)
>>> shorter_side = min(image_h, image_w)
>>> scale = 224. / shorter_side
>>> image_h, image_w = np.ceil([scale * image_h, scale * image_w]).astype('int32')
>>> img = imresize(img, (image_h, image_w))
>>> crop_x = (image_w - 224) / 2
>>> crop_y = (image_h - 224) / 2
>>> img = img[crop_y:crop_y+224,crop_x:crop_x+224,:]
"""
import os
import time
import numpy as np
from scipy.misc import imread, imresize
import tensorflow as tf
import tensorlayer as tl
from tensorlayer.layers import *
try:
from tensorlayer.models.imagenet_classes import *
except Exception as e:
raise Exception(
"{} / download the file from: https://github.com/zsdonghao/tensorlayer/tree/master/example/data".format(e)
)
def conv_layers(net_in):
with tf.name_scope('preprocess'):
# Notice that we include a preprocessing layer that takes the RGB image
# with pixels values in the range of 0-255 and subtracts the mean image
# values (calculated over the entire ImageNet training set).
mean = tf.constant([123.68, 116.779, 103.939], dtype=tf.float32, shape=[1, 1, 1, 3], name='img_mean')
net_in.outputs = net_in.outputs - mean
# conv1
net = Conv2dLayer(net_in, act=tf.nn.relu, shape=[3, 3, 3, 64], strides=[1, 1, 1, 1], padding='SAME', name='conv1_1')
net = Conv2dLayer(net, act=tf.nn.relu, shape=[3, 3, 64, 64], strides=[1, 1, 1, 1], padding='SAME', name='conv1_2')
net = PoolLayer(net, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME', pool=tf.nn.max_pool, name='pool1')
# conv2
net = Conv2dLayer(net, act=tf.nn.relu, shape=[3, 3, 64, 128], strides=[1, 1, 1, 1], padding='SAME', name='conv2_1')
net = Conv2dLayer(net, act=tf.nn.relu, shape=[3, 3, 128, 128], strides=[1, 1, 1, 1], padding='SAME', name='conv2_2')
net = PoolLayer(net, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME', pool=tf.nn.max_pool, name='pool2')
# conv3
net = Conv2dLayer(net, act=tf.nn.relu, shape=[3, 3, 128, 256], strides=[1, 1, 1, 1], padding='SAME', name='conv3_1')
net = Conv2dLayer(net, act=tf.nn.relu, shape=[3, 3, 256, 256], strides=[1, 1, 1, 1], padding='SAME', name='conv3_2')
net = Conv2dLayer(net, act=tf.nn.relu, shape=[3, 3, 256, 256], strides=[1, 1, 1, 1], padding='SAME', name='conv3_3')
net = PoolLayer(net, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME', pool=tf.nn.max_pool, name='pool3')
# conv4
net = Conv2dLayer(net, act=tf.nn.relu, shape=[3, 3, 256, 512], strides=[1, 1, 1, 1], padding='SAME', name='conv4_1')
net = Conv2dLayer(net, act=tf.nn.relu, shape=[3, 3, 512, 512], strides=[1, 1, 1, 1], padding='SAME', name='conv4_2')
net = Conv2dLayer(net, act=tf.nn.relu, shape=[3, 3, 512, 512], strides=[1, 1, 1, 1], padding='SAME', name='conv4_3')
net = PoolLayer(net, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME', pool=tf.nn.max_pool, name='pool4')
# conv5
net = Conv2dLayer(net, act=tf.nn.relu, shape=[3, 3, 512, 512], strides=[1, 1, 1, 1], padding='SAME', name='conv5_1')
net = Conv2dLayer(net, act=tf.nn.relu, shape=[3, 3, 512, 512], strides=[1, 1, 1, 1], padding='SAME', name='conv5_2')
net = Conv2dLayer(net, act=tf.nn.relu, shape=[3, 3, 512, 512], strides=[1, 1, 1, 1], padding='SAME', name='conv5_3')
net = PoolLayer(net, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME', pool=tf.nn.max_pool, name='pool5')
return net
def conv_layers_simple_api(net_in):
with tf.name_scope('preprocess'):
# Notice that we include a preprocessing layer that takes the RGB image
# with pixels values in the range of 0-255 and subtracts the mean image
# values (calculated over the entire ImageNet training set).
mean = tf.constant([123.68, 116.779, 103.939], dtype=tf.float32, shape=[1, 1, 1, 3], name='img_mean')
net_in.outputs = net_in.outputs - mean
# conv1
net = Conv2d(net_in, 64, filter_size=(3, 3), strides=(1, 1), act=tf.nn.relu, padding='SAME', name='conv1_1')
net = Conv2d(net, n_filter=64, filter_size=(3, 3), strides=(1, 1), act=tf.nn.relu, padding='SAME', name='conv1_2')
net = MaxPool2d(net, filter_size=(2, 2), strides=(2, 2), padding='SAME', name='pool1')
# conv2
net = Conv2d(net, n_filter=128, filter_size=(3, 3), strides=(1, 1), act=tf.nn.relu, padding='SAME', name='conv2_1')
net = Conv2d(net, n_filter=128, filter_size=(3, 3), strides=(1, 1), act=tf.nn.relu, padding='SAME', name='conv2_2')
net = MaxPool2d(net, filter_size=(2, 2), strides=(2, 2), padding='SAME', name='pool2')
# conv3
net = Conv2d(net, n_filter=256, filter_size=(3, 3), strides=(1, 1), act=tf.nn.relu, padding='SAME', name='conv3_1')
net = Conv2d(net, n_filter=256, filter_size=(3, 3), strides=(1, 1), act=tf.nn.relu, padding='SAME', name='conv3_2')
net = Conv2d(net, n_filter=256, filter_size=(3, 3), strides=(1, 1), act=tf.nn.relu, padding='SAME', name='conv3_3')
net = MaxPool2d(net, filter_size=(2, 2), strides=(2, 2), padding='SAME', name='pool3')
# conv4
net = Conv2d(net, n_filter=512, filter_size=(3, 3), strides=(1, 1), act=tf.nn.relu, padding='SAME', name='conv4_1')
net = Conv2d(net, n_filter=512, filter_size=(3, 3), strides=(1, 1), act=tf.nn.relu, padding='SAME', name='conv4_2')
net = Conv2d(net, n_filter=512, filter_size=(3, 3), strides=(1, 1), act=tf.nn.relu, padding='SAME', name='conv4_3')
net = MaxPool2d(net, filter_size=(2, 2), strides=(2, 2), padding='SAME', name='pool4')
# conv5
net = Conv2d(net, n_filter=512, filter_size=(3, 3), strides=(1, 1), act=tf.nn.relu, padding='SAME', name='conv5_1')
net = Conv2d(net, n_filter=512, filter_size=(3, 3), strides=(1, 1), act=tf.nn.relu, padding='SAME', name='conv5_2')
net = Conv2d(net, n_filter=512, filter_size=(3, 3), strides=(1, 1), act=tf.nn.relu, padding='SAME', name='conv5_3')
net = MaxPool2d(net, filter_size=(2, 2), strides=(2, 2), padding='SAME', name='pool5')
return net
def fc_layers(net):
net = FlattenLayer(net, name='flatten')
net = DenseLayer(net, n_units=4096, act=tf.nn.relu, name='fc1_relu')
net = DenseLayer(net, n_units=4096, act=tf.nn.relu, name='fc2_relu')
net = DenseLayer(net, n_units=1000, act=tf.identity, name='fc3_relu')
return net
sess = tf.InteractiveSession()
x = tf.placeholder(tf.float32, [None, 224, 224, 3])
# y_ = tf.placeholder(tf.int32, shape=[None, ], name='y_')
net_in = InputLayer(x, name='input')
# net_cnn = conv_layers(net_in) # professional CNN APIs
net_cnn = conv_layers_simple_api(net_in) # simplified CNN APIs
net = fc_layers(net_cnn)
y = net.outputs
probs = tf.nn.softmax(y)
# y_op = tf.argmax(tf.nn.softmax(y), 1)
# cost = tl.cost.cross_entropy(y, y_, name='cost')
# correct_prediction = tf.equal(tf.cast(tf.argmax(y, 1), tf.float32), tf.cast(y_, tf.float32))
# acc = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
tl.layers.initialize_global_variables(sess)
net.print_params()
net.print_layers()
tl.files.maybe_download_and_extract(
'vgg16_weights.npz', 'models', 'http://www.cs.toronto.edu/~frossard/vgg16/', expected_bytes=553436134
)
npz = np.load(os.path.join('models', 'vgg16_weights.npz'))
params = []
for val in sorted(npz.items()):
print(" Loading params %s" % str(val[1].shape))
params.append(val[1])
tl.files.assign_params(sess, params, net)
img1 = imread('data/laska.png', mode='RGB') # test data in github
img1 = imresize(img1, (224, 224))
_ = sess.run(probs, feed_dict={x: [img1]})[0] # 1st time take time to compile
start_time = time.time()
prob = sess.run(probs, feed_dict={x: [img1]})[0]
print(" End time : %.5ss" % (time.time() - start_time))
preds = (np.argsort(prob)[::-1])[0:5]
for p in preds:
print(class_names[p], prob[p])