-
Notifications
You must be signed in to change notification settings - Fork 8
/
utils.py
250 lines (212 loc) · 8.52 KB
/
utils.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
"""
Some codes from https://github.com/Newmu/dcgan_code
"""
from __future__ import division
import math
import json
import random
import pprint
import scipy.misc
import numpy as np
from time import gmtime, strftime
from six.moves import xrange
import tensorflow as tf
import tensorflow.contrib.slim as slim
pp = pprint.PrettyPrinter()
get_stddev = lambda x, k_h, k_w: 1/math.sqrt(k_w*k_h*x.get_shape()[-1])
def show_all_variables():
model_vars = tf.trainable_variables()
slim.model_analyzer.analyze_vars(model_vars, print_info=True)
def get_image(image_path, input_height, input_width,
resize_height=64, resize_width=64,
crop=True, grayscale=False):
image = imread(image_path, grayscale)
return transform(image, input_height, input_width,
resize_height, resize_width, crop)
def save_images(images, size, image_path):
return imsave(inverse_transform(images), size, image_path)
def imread(path, grayscale = False):
if (grayscale):
return scipy.misc.imread(path, flatten = True).astype(np.float)
else:
return scipy.misc.imread(path).astype(np.float)
def merge_images(images, size):
return inverse_transform(images)
def merge(images, size):
h, w = images.shape[1], images.shape[2]
if (images.shape[3] in (3,4)):
c = images.shape[3]
img = np.zeros((h * size[0], w * size[1], c))
for idx, image in enumerate(images):
i = idx % size[1]
j = idx // size[1]
img[j * h:j * h + h, i * w:i * w + w, :] = image
return img
elif images.shape[3]==1:
img = np.zeros((h * size[0], w * size[1]))
for idx, image in enumerate(images):
i = idx % size[1]
j = idx // size[1]
img[j * h:j * h + h, i * w:i * w + w] = image[:,:,0]
return img
else:
raise ValueError('in merge(images,size) images parameter '
'must have dimensions: HxW or HxWx3 or HxWx4')
def imsave(images, size, path):
image = np.squeeze(merge(images, size))
return scipy.misc.imsave(path, image)
def center_crop(x, crop_h, crop_w,
resize_h=64, resize_w=64):
if crop_w is None:
crop_w = crop_h
h, w = x.shape[:2]
j = int(round((h - crop_h)/2.))
i = int(round((w - crop_w)/2.))
return scipy.misc.imresize(
x[j:j+crop_h, i:i+crop_w], [resize_h, resize_w])
def transform(image, input_height, input_width,
resize_height=64, resize_width=64, crop=True):
if crop:
cropped_image = center_crop(
image, input_height, input_width,
resize_height, resize_width)
else:
cropped_image = scipy.misc.imresize(image, [resize_height, resize_width])
return np.array(cropped_image)/127.5 - 1.
def inverse_transform(images):
return (images+1.)/2.
def to_json(output_path, *layers):
with open(output_path, "w") as layer_f:
lines = ""
for w, b, bn in layers:
layer_idx = w.name.split('/')[0].split('h')[1]
B = b.eval()
if "lin/" in w.name:
W = w.eval()
depth = W.shape[1]
else:
W = np.rollaxis(w.eval(), 2, 0)
depth = W.shape[0]
biases = {"sy": 1, "sx": 1, "depth": depth, "w": ['%.2f' % elem for elem in list(B)]}
if bn != None:
gamma = bn.gamma.eval()
beta = bn.beta.eval()
gamma = {"sy": 1, "sx": 1, "depth": depth, "w": ['%.2f' % elem for elem in list(gamma)]}
beta = {"sy": 1, "sx": 1, "depth": depth, "w": ['%.2f' % elem for elem in list(beta)]}
else:
gamma = {"sy": 1, "sx": 1, "depth": 0, "w": []}
beta = {"sy": 1, "sx": 1, "depth": 0, "w": []}
if "lin/" in w.name:
fs = []
for w in W.T:
fs.append({"sy": 1, "sx": 1, "depth": W.shape[0], "w": ['%.2f' % elem for elem in list(w)]})
lines += """
var layer_%s = {
"layer_type": "fc",
"sy": 1, "sx": 1,
"out_sx": 1, "out_sy": 1,
"stride": 1, "pad": 0,
"out_depth": %s, "in_depth": %s,
"biases": %s,
"gamma": %s,
"beta": %s,
"filters": %s
};""" % (layer_idx.split('_')[0], W.shape[1], W.shape[0], biases, gamma, beta, fs)
else:
fs = []
for w_ in W:
fs.append({"sy": 5, "sx": 5, "depth": W.shape[3], "w": ['%.2f' % elem for elem in list(w_.flatten())]})
lines += """
var layer_%s = {
"layer_type": "deconv",
"sy": 5, "sx": 5,
"out_sx": %s, "out_sy": %s,
"stride": 2, "pad": 1,
"out_depth": %s, "in_depth": %s,
"biases": %s,
"gamma": %s,
"beta": %s,
"filters": %s
};""" % (layer_idx, 2**(int(layer_idx)+2), 2**(int(layer_idx)+2),
W.shape[0], W.shape[3], biases, gamma, beta, fs)
layer_f.write(" ".join(lines.replace("'","").split()))
def make_gif(images, fname, duration=2, true_image=False):
import moviepy.editor as mpy
def make_frame(t):
try:
x = images[int(len(images)/duration*t)]
except:
x = images[-1]
if true_image:
return x.astype(np.uint8)
else:
return ((x+1)/2*255).astype(np.uint8)
clip = mpy.VideoClip(make_frame, duration=duration)
clip.write_gif(fname, fps = len(images) / duration)
def visualize(sess, dcgan, config, option):
image_frame_dim = int(math.ceil(config.batch_size**.5))
if option == 0:
z_sample = np.random.uniform(-0.5, 0.5, size=(config.batch_size, dcgan.z_dim))
samples = sess.run(dcgan.sampler, feed_dict={dcgan.z: z_sample})
save_images(samples, [image_frame_dim, image_frame_dim], './samples/test_%s.png' % strftime("%Y-%m-%d-%H-%M-%S", gmtime()))
elif option == 1:
values = np.arange(0, 1, 1./config.batch_size)
for idx in xrange(dcgan.z_dim):
print(" [*] %d" % idx)
z_sample = np.random.uniform(-1, 1, size=(config.batch_size , dcgan.z_dim))
for kdx, z in enumerate(z_sample):
z[idx] = values[kdx]
if config.dataset == "mnist":
y = np.random.choice(10, config.batch_size)
y_one_hot = np.zeros((config.batch_size, 10))
y_one_hot[np.arange(config.batch_size), y] = 1
samples = sess.run(dcgan.sampler, feed_dict={dcgan.z: z_sample, dcgan.y: y_one_hot})
else:
samples = sess.run(dcgan.sampler, feed_dict={dcgan.z: z_sample})
save_images(samples, [image_frame_dim, image_frame_dim], './samples/test_arange_%s.png' % (idx))
elif option == 2:
values = np.arange(0, 1, 1./config.batch_size)
for idx in [random.randint(0, dcgan.z_dim - 1) for _ in xrange(dcgan.z_dim)]:
print(" [*] %d" % idx)
z = np.random.uniform(-0.2, 0.2, size=(dcgan.z_dim))
z_sample = np.tile(z, (config.batch_size, 1))
#z_sample = np.zeros([config.batch_size, dcgan.z_dim])
for kdx, z in enumerate(z_sample):
z[idx] = values[kdx]
if config.dataset == "mnist":
y = np.random.choice(10, config.batch_size)
y_one_hot = np.zeros((config.batch_size, 10))
y_one_hot[np.arange(config.batch_size), y] = 1
samples = sess.run(dcgan.sampler, feed_dict={dcgan.z: z_sample, dcgan.y: y_one_hot})
else:
samples = sess.run(dcgan.sampler, feed_dict={dcgan.z: z_sample})
try:
make_gif(samples, './samples/test_gif_%s.gif' % (idx))
except:
save_images(samples, [image_frame_dim, image_frame_dim], './samples/test_%s.png' % strftime("%Y-%m-%d-%H-%M-%S", gmtime()))
elif option == 3:
values = np.arange(0, 1, 1./config.batch_size)
for idx in xrange(dcgan.z_dim):
print(" [*] %d" % idx)
z_sample = np.zeros([config.batch_size, dcgan.z_dim])
for kdx, z in enumerate(z_sample):
z[idx] = values[kdx]
samples = sess.run(dcgan.sampler, feed_dict={dcgan.z: z_sample})
make_gif(samples, './samples/test_gif_%s.gif' % (idx))
elif option == 4:
image_set = []
values = np.arange(0, 1, 1./config.batch_size)
for idx in xrange(dcgan.z_dim):
print(" [*] %d" % idx)
z_sample = np.zeros([config.batch_size, dcgan.z_dim])
for kdx, z in enumerate(z_sample): z[idx] = values[kdx]
image_set.append(sess.run(dcgan.sampler, feed_dict={dcgan.z: z_sample}))
make_gif(image_set[-1], './samples/test_gif_%s.gif' % (idx))
new_image_set = [merge(np.array([images[idx] for images in image_set]), [10, 10]) \
for idx in range(64) + range(63, -1, -1)]
make_gif(new_image_set, './samples/test_gif_merged.gif', duration=8)
def image_manifold_size(num_images):
manifold_h = int(np.floor(np.sqrt(num_images)))
manifold_w = int(np.ceil(np.sqrt(num_images)))
assert manifold_h * manifold_w == num_images
return manifold_h, manifold_w