forked from ShawkhIbneRashid/medical-images-sr
-
Notifications
You must be signed in to change notification settings - Fork 0
/
utils.py
187 lines (159 loc) · 7.4 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
import cv2
import math
import numpy as np
import os
import torch
from basicsr.archs.rrdbnet_arch import RRDBNet
from torch.hub import download_url_to_file, get_dir
from torch.nn import functional as F
from urllib.parse import urlparse
ROOT_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
class RealESRGANer():
def __init__(self, scale, model_path, model=None, tile=0, tile_pad=10, pre_pad=10, half=False):
self.scale = scale
self.tile_size = tile
self.tile_pad = tile_pad
self.pre_pad = pre_pad
self.mod_scale = None
self.half = half
# initialize model
self.device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
if model is None:
model = RRDBNet(num_in_ch=1, num_out_ch=1, num_feat=64, num_block=23, num_grow_ch=32, scale=scale)
if model_path.startswith('https://'):
model_path = load_file_from_url(
url=model_path, model_dir='realesrgan/weights', progress=True, file_name=None)
loadnet = torch.load(model_path)
if 'params_ema' in loadnet:
keyname = 'params_ema'
else:
keyname = 'params'
model.load_state_dict(loadnet[keyname], strict=True)
model.eval()
self.model = model.to(self.device)
if self.half:
self.model = self.model.half()
def pre_process(self, img):
img = torch.from_numpy(np.transpose(img, (2, 0, 1))).float()
self.img = img.unsqueeze(0).to(self.device)
if self.half:
self.img = self.img.half()
# pre_pad
if self.pre_pad != 0:
self.img = F.pad(self.img, (0, self.pre_pad, 0, self.pre_pad), 'reflect')
# mod pad
if self.scale == 2:
self.mod_scale = 2
elif self.scale == 1:
self.mod_scale = 4
if self.mod_scale is not None:
self.mod_pad_h, self.mod_pad_w = 0, 0
_, _, h, w = self.img.size()
if (h % self.mod_scale != 0):
self.mod_pad_h = (self.mod_scale - h % self.mod_scale)
if (w % self.mod_scale != 0):
self.mod_pad_w = (self.mod_scale - w % self.mod_scale)
self.img = F.pad(self.img, (0, self.mod_pad_w, 0, self.mod_pad_h), 'reflect')
def process(self):
#self.img =
self.output = self.model(self.img)
def tile_process(self):
"""Modified from: https://github.com/ata4/esrgan-launcher
"""
batch, channel, height, width = self.img.shape
output_height = height * self.scale
output_width = width * self.scale
output_shape = (batch, channel, output_height, output_width)
# start with black image
self.output = self.img.new_zeros(output_shape)
tiles_x = math.ceil(width / self.tile_size)
tiles_y = math.ceil(height / self.tile_size)
# loop over all tiles
for y in range(tiles_y):
for x in range(tiles_x):
# extract tile from input image
ofs_x = x * self.tile_size
ofs_y = y * self.tile_size
# input tile area on total image
input_start_x = ofs_x
input_end_x = min(ofs_x + self.tile_size, width)
input_start_y = ofs_y
input_end_y = min(ofs_y + self.tile_size, height)
# input tile area on total image with padding
input_start_x_pad = max(input_start_x - self.tile_pad, 0)
input_end_x_pad = min(input_end_x + self.tile_pad, width)
input_start_y_pad = max(input_start_y - self.tile_pad, 0)
input_end_y_pad = min(input_end_y + self.tile_pad, height)
# input tile dimensions
input_tile_width = input_end_x - input_start_x
input_tile_height = input_end_y - input_start_y
tile_idx = y * tiles_x + x + 1
input_tile = self.img[:, :, input_start_y_pad:input_end_y_pad, input_start_x_pad:input_end_x_pad]
# upscale tile
try:
with torch.no_grad():
output_tile = self.model(input_tile)
except Exception as error:
print('Error', error)
print(f'\tTile {tile_idx}/{tiles_x * tiles_y}')
# output tile area on total image
output_start_x = input_start_x * self.scale
output_end_x = input_end_x * self.scale
output_start_y = input_start_y * self.scale
output_end_y = input_end_y * self.scale
# output tile area without padding
output_start_x_tile = (input_start_x - input_start_x_pad) * self.scale
output_end_x_tile = output_start_x_tile + input_tile_width * self.scale
output_start_y_tile = (input_start_y - input_start_y_pad) * self.scale
output_end_y_tile = output_start_y_tile + input_tile_height * self.scale
# put tile into output image
self.output[:, :, output_start_y:output_end_y,
output_start_x:output_end_x] = output_tile[:, :, output_start_y_tile:output_end_y_tile,
output_start_x_tile:output_end_x_tile]
def post_process(self):
# remove extra pad
if self.mod_scale is not None:
_, _, h, w = self.output.size()
self.output = self.output[:, :, 0:h - self.mod_pad_h * self.scale, 0:w - self.mod_pad_w * self.scale]
# remove prepad
if self.pre_pad != 0:
_, _, h, w = self.output.size()
self.output = self.output[:, :, 0:h - self.pre_pad * self.scale, 0:w - self.pre_pad * self.scale]
return self.output
@torch.no_grad()
def enhance(self, img, outscale=None, alpha_upsampler='realesrgan'):
h_input, w_input = img.shape[0:2]
img = img.astype(np.float32)
# ------------------- process image (without the alpha channel) ------------------- #
self.pre_process(img)
if self.tile_size > 0:
self.tile_process()
else:
self.process()
output_img = self.post_process()
output_img = output_img.data.squeeze().float().cpu().clamp_(0, 1).numpy()
if outscale is not None and outscale != float(self.scale):
output = cv2.resize(
output_img, (
int(w_input * outscale),
int(h_input * outscale),
), interpolation=cv2.INTER_LANCZOS4)
print('yes')
print(outscale)
return output_img
def load_file_from_url(url, model_dir=None, progress=True, file_name=None):
"""Ref:https://github.com/1adrianb/face-alignment/blob/master/face_alignment/utils.py
"""
if model_dir is None:
hub_dir = get_dir()
model_dir = os.path.join(hub_dir, 'checkpoints')
os.makedirs(os.path.join(ROOT_DIR, model_dir), exist_ok=True)
parts = urlparse(url)
filename = os.path.basename(parts.path)
if file_name is not None:
filename = file_name
cached_file = os.path.abspath(os.path.join(ROOT_DIR, model_dir, filename))
if not os.path.exists(cached_file):
print(f'Downloading: "{url}" to {cached_file}\n')
download_url_to_file(url, cached_file, hash_prefix=None, progress=progress)
return cached_file