Spaces:
Running
Running
File size: 7,700 Bytes
2514fb4 |
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 |
import os.path
import logging
import re
import numpy as np
from collections import OrderedDict
import torch
from utils import utils_logger
from utils import utils_image as util
from utils import utils_model
'''
Spyder (Python 3.6)
PyTorch 1.1.0
Windows 10 or Linux
Kai Zhang ([email protected])
github: https://github.com/cszn/KAIR
If you have any question, please feel free to contact with me.
Kai Zhang (e-mail: [email protected])
(github: https://github.com/cszn/KAIR)
by Kai Zhang (12/Dec./2019)
'''
"""
# --------------------------------------------
testing demo for RRDB-ESRGAN
https://github.com/xinntao/ESRGAN
@inproceedings{wang2018esrgan,
title={Esrgan: Enhanced super-resolution generative adversarial networks},
author={Wang, Xintao and Yu, Ke and Wu, Shixiang and Gu, Jinjin and Liu, Yihao and Dong, Chao and Qiao, Yu and Change Loy, Chen},
booktitle={European Conference on Computer Vision (ECCV)},
pages={0--0},
year={2018}
}
# --------------------------------------------
|--model_zoo # model_zoo
|--rrdb_x4_esrgan # model_name, optimized for perceptual quality
|--rrdb_x4_psnr # model_name, optimized for PSNR
|--testset # testsets
|--set5 # testset_name
|--srbsd68
|--results # results
|--set5_rrdb_x4_esrgan# result_name = testset_name + '_' + model_name
|--set5_rrdb_x4_psnr
# --------------------------------------------
"""
def main():
# ----------------------------------------
# Preparation
# ----------------------------------------
model_name = 'rrdb_x4_esrgan' # 'rrdb_x4_esrgan' | 'rrdb_x4_psnr'
testset_name = 'set5' # test set, 'set5' | 'srbsd68'
need_degradation = True # default: True
x8 = False # default: False, x8 to boost performance
sf = [int(s) for s in re.findall(r'\d+', model_name)][0] # scale factor
show_img = False # default: False
task_current = 'sr' # 'dn' for denoising | 'sr' for super-resolution
n_channels = 3 # fixed
model_pool = 'model_zoo' # fixed
testsets = 'testsets' # fixed
results = 'results' # fixed
noise_level_img = 0 # fixed: 0, noise level for LR image
result_name = testset_name + '_' + model_name
border = sf if task_current == 'sr' else 0 # shave boader to calculate PSNR and SSIM
model_path = os.path.join(model_pool, model_name+'.pth')
# ----------------------------------------
# L_path, E_path, H_path
# ----------------------------------------
L_path = os.path.join(testsets, testset_name) # L_path, for Low-quality images
H_path = L_path # H_path, for High-quality images
E_path = os.path.join(results, result_name) # E_path, for Estimated images
util.mkdir(E_path)
if H_path == L_path:
need_degradation = True
logger_name = result_name
utils_logger.logger_info(logger_name, log_path=os.path.join(E_path, logger_name+'.log'))
logger = logging.getLogger(logger_name)
need_H = True if H_path is not None else False
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
# ----------------------------------------
# load model
# ----------------------------------------
from models.network_rrdb import RRDB as net
model = net(in_nc=n_channels, out_nc=n_channels, nc=64, nb=23, gc=32, upscale=4, act_mode='L', upsample_mode='upconv')
model.load_state_dict(torch.load(model_path), strict=True) # strict=False
model.eval()
for k, v in model.named_parameters():
v.requires_grad = False
model = model.to(device)
logger.info('Model path: {:s}'.format(model_path))
number_parameters = sum(map(lambda x: x.numel(), model.parameters()))
logger.info('Params number: {}'.format(number_parameters))
test_results = OrderedDict()
test_results['psnr'] = []
test_results['ssim'] = []
test_results['psnr_y'] = []
test_results['ssim_y'] = []
logger.info('model_name:{}, image sigma:{}'.format(model_name, noise_level_img))
logger.info(L_path)
L_paths = util.get_image_paths(L_path)
H_paths = util.get_image_paths(H_path) if need_H else None
for idx, img in enumerate(L_paths):
# ------------------------------------
# (1) img_L
# ------------------------------------
img_name, ext = os.path.splitext(os.path.basename(img))
# logger.info('{:->4d}--> {:>10s}'.format(idx+1, img_name+ext))
img_L = util.imread_uint(img, n_channels=n_channels)
img_L = util.uint2single(img_L)
# degradation process, bicubic downsampling + Gaussian noise
if need_degradation:
img_L = util.modcrop(img_L, sf)
img_L = util.imresize_np(img_L, 1/sf)
# np.random.seed(seed=0) # for reproducibility
# img_L += np.random.normal(0, noise_level_img/255., img_L.shape)
util.imshow(util.single2uint(img_L), title='LR image with noise level {}'.format(noise_level_img)) if show_img else None
img_L = util.single2tensor4(img_L)
img_L = img_L.to(device)
# ------------------------------------
# (2) img_E
# ------------------------------------
if not x8:
img_E = model(img_L)
else:
img_E = utils_model.test_mode(model, img_L, mode=3, sf=sf)
img_E = util.tensor2uint(img_E)
if need_H:
# --------------------------------
# (3) img_H
# --------------------------------
img_H = util.imread_uint(H_paths[idx], n_channels=n_channels)
img_H = img_H.squeeze()
img_H = util.modcrop(img_H, sf)
# --------------------------------
# PSNR and SSIM
# --------------------------------
psnr = util.calculate_psnr(img_E, img_H, border=border)
ssim = util.calculate_ssim(img_E, img_H, border=border)
test_results['psnr'].append(psnr)
test_results['ssim'].append(ssim)
logger.info('{:s} - PSNR: {:.2f} dB; SSIM: {:.4f}.'.format(img_name+ext, psnr, ssim))
util.imshow(np.concatenate([img_E, img_H], axis=1), title='Recovered / Ground-truth') if show_img else None
if np.ndim(img_H) == 3: # RGB image
img_E_y = util.rgb2ycbcr(img_E, only_y=True)
img_H_y = util.rgb2ycbcr(img_H, only_y=True)
psnr_y = util.calculate_psnr(img_E_y, img_H_y, border=border)
ssim_y = util.calculate_ssim(img_E_y, img_H_y, border=border)
test_results['psnr_y'].append(psnr_y)
test_results['ssim_y'].append(ssim_y)
# ------------------------------------
# save results
# ------------------------------------
util.imsave(img_E, os.path.join(E_path, img_name+'.png'))
if need_H:
ave_psnr = sum(test_results['psnr']) / len(test_results['psnr'])
ave_ssim = sum(test_results['ssim']) / len(test_results['ssim'])
logger.info('Average PSNR/SSIM(RGB) - {} - x{} --PSNR: {:.2f} dB; SSIM: {:.4f}'.format(result_name, sf, ave_psnr, ave_ssim))
if np.ndim(img_H) == 3:
ave_psnr_y = sum(test_results['psnr_y']) / len(test_results['psnr_y'])
ave_ssim_y = sum(test_results['ssim_y']) / len(test_results['ssim_y'])
logger.info('Average PSNR/SSIM( Y ) - {} - x{} - PSNR: {:.2f} dB; SSIM: {:.4f}'.format(result_name, sf, ave_psnr_y, ave_ssim_y))
if __name__ == '__main__':
main()
|