forked from LimingXuM3/BPGAN
-
Notifications
You must be signed in to change notification settings - Fork 0
/
utils.py
270 lines (223 loc) · 9.52 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
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
# -*- coding: utf-8 -*-
"""
Created on Mon Sep 9 15:29:18 2019
@author: He Zhang
"""
# define some custom function for BPGAN model
from __future__ import print_function
import torch
import numpy as np
from PIL import Image
import os
import cv2
from numpy.lib.stride_tricks import as_strided
import scipy.sparse
import scipy.sparse.linalg
from math import exp
import torch.nn.functional as F
from torch.autograd import Variable
import random
import dominate
from dominate.tags import meta, h3, table, tr, td, p, a, img, br
def tensor2im(input_image, imtype=np.uint8):
if not isinstance(input_image, np.ndarray):
if isinstance(input_image, torch.Tensor): # get the data from a variable
image_tensor = input_image.data
else:
return input_image
image_numpy = image_tensor[0].cpu().float().numpy() # convert it into a numpy array
if image_numpy.shape[0] == 1: # grayscale to RGB
image_numpy = np.tile(image_numpy, (3, 1, 1))
image_numpy = (np.transpose(image_numpy, (1, 2, 0)) + 1) / 2.0 * 255.0 # post-processing: tranpose and scaling
else: # if it is a numpy array, do nothing
image_numpy = input_image
return image_numpy.astype(imtype)
def diagnose_network(net, name='network'):
mean = 0.0
count = 0
for param in net.parameters():
if param.grad is not None:
mean += torch.mean(torch.abs(param.grad.data))
count += 1
if count > 0:
mean = mean / count
print(name)
print(mean)
def save_image(image_numpy, image_path):
image_pil = Image.fromarray(image_numpy)
image_pil.save(image_path)
def print_numpy(x, val=True, shp=False):
x = x.astype(np.float64)
if shp:
print('shape,', x.shape)
if val:
x = x.flatten()
print('mean = %3.3f, min = %3.3f, max = %3.3f, median = %3.3f, std=%3.3f' % (
np.mean(x), np.min(x), np.max(x), np.median(x), np.std(x)))
def mkdirs(paths):
if isinstance(paths, list) and not isinstance(paths, str):
for path in paths:
mkdir(path)
else:
mkdir(paths)
def mkdir(path):
if not os.path.exists(path):
os.makedirs(path)
def compute_lap(path_img):
image = path_img.mul(255).byte()
image = image.cpu().numpy().transpose((1, 2, 0))
image = 1.0 * image / 255.0
h, w, _ = image.shape
M = compute_laplacian(image)
M = M.tocoo().astype(np.float32)
indices = torch.from_numpy(np.vstack((M.row, M.col))).long().cuda()
values = torch.from_numpy(M.data).cuda()
shape = torch.Size(M.shape)
Ms = torch.sparse_coo_tensor(indices, values, shape, device=torch.device('cuda'))
return Ms
def _rolling_block(A, block=(3, 3)):
shape = (A.shape[0] - block[0] + 1, A.shape[1] - block[1] + 1) + block
strides = (A.strides[0], A.strides[1]) + A.strides
return as_strided(A, shape=shape, strides=strides)
def compute_laplacian(img, mask=None, eps=10 ** (-7), win_rad=1):
win_size = (win_rad * 2 + 1) ** 2
h, w, d = img.shape
# Number of window centre indices in h, w axes
c_h, c_w = h - 2 * win_rad, w - 2 * win_rad
win_diam = win_rad * 2 + 1
indsM = np.arange(h * w).reshape((h, w))
ravelImg = img.reshape(h * w, d)
win_inds = _rolling_block(indsM, block=(win_diam, win_diam))
win_inds = win_inds.reshape(c_h, c_w, win_size)
if mask is not None:
mask = cv2.dilate(
mask.astype(np.uint8),
np.ones((win_diam, win_diam), np.uint8)
).astype(np.bool)
win_mask = np.sum(mask.ravel()[win_inds], axis=2)
win_inds = win_inds[win_mask > 0, :]
else:
win_inds = win_inds.reshape(-1, win_size)
winI = ravelImg[win_inds]
win_mu = np.mean(winI, axis=1, keepdims=True)
win_var = np.einsum('...ji,...jk ->...ik', winI, winI) / win_size - np.einsum('...ji,...jk ->...ik', win_mu, win_mu)
inv = np.linalg.inv(win_var + (eps / win_size) * np.eye(3))
X = np.einsum('...ij,...jk->...ik', winI - win_mu, inv)
vals = np.eye(win_size) - (1.0 / win_size) * (1 + np.einsum('...ij,...kj->...ik', X, winI - win_mu))
nz_indsCol = np.tile(win_inds, win_size).ravel()
nz_indsRow = np.repeat(win_inds, win_size).ravel()
nz_indsVal = vals.ravel()
L = scipy.sparse.coo_matrix((nz_indsVal, (nz_indsRow, nz_indsCol)), shape=(h * w, h * w))
return L
def gaussian(window_size, sigma):
gauss = torch.Tensor([exp(-(x - window_size // 2) ** 2 / float(2 * sigma ** 2)) for x in range(window_size)])
return gauss / gauss.sum()
def create_window(window_size, channel):
_1D_window = gaussian(window_size, 1.5).unsqueeze(1)
_2D_window = _1D_window.mm(_1D_window.t()).float().unsqueeze(0).unsqueeze(0)
window = Variable(_2D_window.expand(channel, 1, window_size, window_size).contiguous())
return window
def _ssim(img1, img2, window, window_size, channel, size_average=True):
mu1 = F.conv2d(img1, window, padding=window_size // 2, groups=channel)
mu2 = F.conv2d(img2, window, padding=window_size // 2, groups=channel)
mu1_sq = mu1.pow(2)
mu2_sq = mu2.pow(2)
mu1_mu2 = mu1 * mu2
sigma1_sq = F.conv2d(img1 * img1, window, padding=window_size // 2, groups=channel) - mu1_sq
sigma2_sq = F.conv2d(img2 * img2, window, padding=window_size // 2, groups=channel) - mu2_sq
sigma12 = F.conv2d(img1 * img2, window, padding=window_size // 2, groups=channel) - mu1_mu2
C1 = 0.01 ** 2
C2 = 0.03 ** 2
ssim_map = ((2 * mu1_mu2 + C1) * (2 * sigma12 + C2)) / ((mu1_sq + mu2_sq + C1) * (sigma1_sq + sigma2_sq + C2))
if size_average:
return ssim_map.mean()
else:
return ssim_map.mean(1).mean(1).mean(1)
class SSIM(torch.nn.Module):
def __init__(self, window_size=11, size_average=True):
super(SSIM, self).__init__()
self.window_size = window_size
self.size_average = size_average
self.channel = 1
self.window = create_window(window_size, self.channel)
def forward(self, img1, img2):
(_, channel, _, _) = img1.size()
if channel == self.channel and self.window.data.type() == img1.data.type():
window = self.window
else:
window = create_window(self.window_size, channel)
if img1.is_cuda:
window = window.cuda(img1.get_device())
window = window.type_as(img1)
self.window = window
self.channel = channel
return _ssim(img1, img2, window, self.window_size, channel, self.size_average)
def ssim(img1, img2, window_size=11, size_average=True):
(_, channel, _, _) = img1.size()
window = create_window(window_size, channel)
if img1.is_cuda:
window = window.cuda(img1.get_device())
window = window.type_as(img1)
return _ssim(img1, img2, window, window_size, channel, size_average)
class ImagePool():
def __init__(self, pool_size):
self.pool_size = pool_size
if self.pool_size > 0: # create an empty pool
self.num_imgs = 0
self.images = []
def query(self, images):
if self.pool_size == 0: # if the buffer size is 0, do nothing
return images
return_images = []
for image in images:
image = torch.unsqueeze(image.data, 0)
if self.num_imgs < self.pool_size: # if the buffer is not full; keep inserting current images to the buffer
self.num_imgs = self.num_imgs + 1
self.images.append(image)
return_images.append(image)
else:
p = random.uniform(0, 1)
if p > 0.5: # by 50% chance, the buffer will return a previously stored image, and insert the current image into the buffer
random_id = random.randint(0, self.pool_size - 1) # randint is inclusive
tmp = self.images[random_id].clone()
self.images[random_id] = image
return_images.append(tmp)
else: # by another 50% chance, the buffer will return the current image
return_images.append(image)
return_images = torch.cat(return_images, 0) # collect all the images and return
return return_images
class HTML:
def __init__(self, web_dir, title, refresh=0):
self.title = title
self.web_dir = web_dir
self.img_dir = os.path.join(self.web_dir, 'images')
if not os.path.exists(self.web_dir):
os.makedirs(self.web_dir)
if not os.path.exists(self.img_dir):
os.makedirs(self.img_dir)
self.doc = dominate.document(title=title)
if refresh > 0:
with self.doc.head:
meta(http_equiv="refresh", content=str(refresh))
def get_image_dir(self):
return self.img_dir
def add_header(self, text):
with self.doc:
h3(text)
def add_images(self, ims, txts, links, width=400):
self.t = table(border=1, style="table-layout: fixed;") # Insert a table
self.doc.add(self.t)
with self.t:
with tr():
for im, txt, link in zip(ims, txts, links):
with td(style="word-wrap: break-word;", halign="center", valign="top"):
with p():
with a(href=os.path.join('images', link)):
img(style="width:%dpx" % width, src=os.path.join('images', im))
br()
p(txt)
def save(self):
html_file = '%s/index.html' % self.web_dir
f = open(html_file, 'wt')
f.write(self.doc.render())
f.close()