def __init__(self, opt):
super(DatasetPlainPatch, self).__init__()
print(
'Get L/H for image-to-image mapping. Both "paths_L" and "paths_H" are needed.'
)
self.opt = opt
self.n_channels = opt['n_channels'] if opt['n_channels'] else 3
self.patch_size = self.opt['H_size'] if self.opt['H_size'] else 64
self.num_patches_per_image = opt['num_patches_per_image'] if opt[
'num_patches_per_image'] else 40
self.num_sampled = opt['num_sampled'] if opt['num_sampled'] else 3000
# -------------------
# get the path of L/H
# -------------------
self.paths_H = util.get_image_paths(opt['dataroot_H'])
self.paths_L = util.get_image_paths(opt['dataroot_L'])
assert self.paths_H, 'Error: H path is empty.'
assert self.paths_L, 'Error: L path is empty. This dataset uses L path, you can use dataset_dnpatchh'
if self.paths_L and self.paths_H:
assert len(self.paths_L) == len(
self.paths_H
), 'H and L datasets have different number of images - {}, {}.'.format(
len(self.paths_L), len(self.paths_H))
# ------------------------------------
# number of sampled images
# ------------------------------------
self.num_sampled = min(self.num_sampled, len(self.paths_H))
# ------------------------------------
# reserve space with zeros
# ------------------------------------
self.total_patches = self.num_sampled * self.num_patches_per_image
self.H_data = np.zeros([
self.total_patches, self.path_size, self.path_size, self.n_channels
],
dtype=np.uint8)
self.L_data = np.zeros([
self.total_patches, self.path_size, self.path_size, self.n_channels
],
dtype=np.uint8)
# ------------------------------------
# update H patches
# ------------------------------------
self.update_data()
def general_image_folder(opt):
therwise, it will store every resolution info.
img_folder = opt['img_folder']
lmdb_save_path = opt['lmdb_save_path']
meta_info = {'name': opt['name']}
if not lmdb_save_path.endswith('.lmdb'):
raise ValueError("lmdb_save_path must end with 'lmdb'.")
if os.path.exists(lmdb_save_path):
print('Folder [{:s}] already exists. Exit...'.format(lmdb_save_path))
sys.exit(1)
# read all the image paths to a list
print('Reading image path list ...')
all_img_list = util.get_image_paths(img_folder)
keys = []
for img_path in all_img_list:
img_path_split = img_path.split('/')[-2:]
img_name_ext = img_path_split[0] + '_' + img_path_split[1]
img_name, ext = os.path.splitext(img_name_ext)
keys.append(img_name)
data_size_per_img = cv2.imread(all_img_list[0], cv2.IMREAD_UNCHANGED).nbytes
print('data size per image is: ', data_size_per_img)
data_size = data_size_per_img * len(all_img_list)
env = lmdb.open(lmdb_save_path, map_size=data_size * 10)
txn = env.begin(write=True)
resolutions = []
tqdm_iter = tqdm(enumerate(zip(all_img_list, keys)), total=len(all_img_list), leave=False)
for idx, (path, key) in tqdm_iter:
tqdm_iter.set_description('Write {}'.format(key))
key_byte = key.encode('ascii')
data = util.imread_uint(path, 3)
H, W, C = data.shape
resolutions.append('{:d}_{:d}_{:d}'.format(C, H, W))
txn.put(key_byte, data)
if (idx + 1) % opt['commit_interval'] == 0:
txn.commit()
txn = env.begin(write=True)
txn.commit()
env.close()
print('Finish writing lmdb.')
assert len(keys) == len(resolutions)
if len(set(resolutions)) <= 1:
meta_info['resolution'] = [resolutions[0]]
meta_info['keys'] = keys
print('All images have the same resolution. Simplify the meta info.')
else:
meta_info['resolution'] = resolutions
meta_info['keys'] = keys
print('Not all images have the same resolution. Save meta info for each image.')
pickle.dump(meta_info, open(os.path.join(lmdb_save_path, 'meta_info.pkl'), "wb"))
print('Finish creating lmdb meta info.')
def __init__(self, opt):
super(DatasetSR, self).__init__()
self.opt = opt
self.n_channels = opt['n_channels'] if opt['n_channels'] else 3
self.sf = opt['scale'] if opt['scale'] else 4
self.patch_size = self.opt['H_size'] if self.opt['H_size'] else 96
self.L_size = self.patch_size // self.sf
# ------------------------------------
# get paths of L/H
# ------------------------------------
self.paths_H = util.get_image_paths(opt['dataroot_H'])
self.paths_L = util.get_image_paths(opt['dataroot_L'])
assert self.paths_H, 'Error: H path is empty.'
if self.paths_L and self.paths_H:
assert len(self.paths_L) == len(self.paths_H), 'L/H mismatch - {}, {}.'.format(len(self.paths_L), len(self.paths_H))
def __init__(self, opt):
super(DatasetPlain, self).__init__()
print('Get L/H for image-to-image mapping. Both "paths_L" and "paths_H" are needed.')
self.opt = opt
self.n_channels = opt['n_channels'] if opt['n_channels'] else 3
self.patch_size = self.opt['H_size'] if self.opt['H_size'] else 64
# ------------------------------------
# get the path of L/H
# ------------------------------------
self.paths_H = util.get_image_paths(opt['dataroot_H'])
self.paths_L = util.get_image_paths(opt['dataroot_L'])
assert self.paths_H, 'Error: H path is empty.'
assert self.paths_L, 'Error: L path is empty. Plain dataset assumes both L and H are given!'
if self.paths_L and self.paths_H:
assert len(self.paths_L) == len(self.paths_H), 'L/H mismatch - {}, {}.'.format(len(self.paths_L), len(self.paths_H))
def __init__(self, opt):
super(DatasetDPSR, self).__init__()
self.opt = opt
self.n_channels = opt['n_channels'] if opt['n_channels'] else 3
self.sf = opt['scale'] if opt['scale'] else 4
self.patch_size = self.opt['H_size'] if self.opt['H_size'] else 96
self.L_size = self.patch_size // self.sf
self.sigma = opt['sigma'] if opt['sigma'] else [0, 50]
self.sigma_min, self.sigma_max = self.sigma[0], self.sigma[1]
self.sigma_test = opt['sigma_test'] if opt['sigma_test'] else 0
# ------------------------------------
# get paths of L/H
# ------------------------------------
self.paths_H = util.get_image_paths(opt['dataroot_H'])
self.paths_L = util.get_image_paths(opt['dataroot_L'])
assert self.paths_H, 'Error: H path is empty.'
def __init__(self, opt):
super(DatasetL, self).__init__()
print('Read L in testing. Only "dataroot_L" is needed.')
self.opt = opt
self.n_channels = opt['n_channels'] if opt['n_channels'] else 3
# ------------------------------------
# get the path of L
# ------------------------------------
self.paths_L = util.get_image_paths(opt['dataroot_L'])
assert self.paths_L, 'Error: L paths are empty.'
def __init__(self, opt):
super(DatasetFFDNet, self).__init__()
self.opt = opt
self.n_channels = opt['n_channels'] if opt['n_channels'] else 3
self.patch_size = self.opt['H_size'] if opt['H_size'] else 64
self.sigma = opt['sigma'] if opt['sigma'] else [0, 75]
self.sigma_min, self.sigma_max = self.sigma[0], self.sigma[1]
self.sigma_test = opt['sigma_test'] if opt['sigma_test'] else 25
# -------------------------------------
# get the path of H, return None if input is None
# -------------------------------------
self.paths_H = util.get_image_paths(opt['dataroot_H'])
def __init__(self, opt):
super(DatasetSRMD, self).__init__()
self.opt = opt
self.n_channels = opt['n_channels'] if opt['n_channels'] else 3
self.sf = opt['scale'] if opt['scale'] else 4
self.patch_size = self.opt['H_size'] if self.opt['H_size'] else 96
self.L_size = self.patch_size // self.sf
self.sigma = opt['sigma'] if opt['sigma'] else [0, 50]
self.sigma_min, self.sigma_max = self.sigma[0], self.sigma[1]
self.sigma_test = opt['sigma_test'] if opt['sigma_test'] else 0
# -------------------------------------
# PCA projection matrix
# -------------------------------------
self.p = hdf5storage.loadmat(os.path.join('kernels', 'srmd_pca_pytorch.mat'))['p']
self.ksize = int(np.sqrt(self.p.shape[-1])) # kernel size
# ------------------------------------
# get paths of L/H
# ------------------------------------
self.paths_H = util.get_image_paths(opt['dataroot_H'])
self.paths_L = util.get_image_paths(opt['dataroot_L'])
def __init__(self, opt):
super(DatasetDnCNN, self).__init__()
print(
'Dataset: Denosing on AWGN with fixed sigma. Only dataroot_H is needed.'
)
self.opt = opt
self.n_channels = opt['n_channels'] if opt['n_channels'] else 3
self.patch_size = opt['H_size'] if opt['H_size'] else 64
self.sigma = opt['sigma'] if opt['sigma'] else 25
self.sigma_test = opt['sigma_test'] if opt['sigma_test'] else self.sigma
# ------------------------------------
# get path of H
# return None if input is None
# ------------------------------------
self.paths_H = util.get_image_paths(opt['dataroot_H'])
def __init__(self, opt):
super(DatasetUSRNet, self).__init__()
self.opt = opt
self.n_channels = opt['n_channels'] if opt['n_channels'] else 3
self.patch_size = self.opt['H_size'] if self.opt['H_size'] else 96
self.sigma_max = self.opt['sigma_max'] if self.opt['sigma_max'] is not None else 25
self.scales = opt['scales'] if opt['scales'] is not None else [1,2,3,4]
self.sf_validation = opt['sf_validation'] if opt['sf_validation'] is not None else 3
#self.kernels = hdf5storage.loadmat(os.path.join('kernels', 'kernels_12.mat'))['kernels']
self.kernels = loadmat(os.path.join('kernels', 'kernels_12.mat'))['kernels'] # for validation
# -------------------
# get the path of H
# -------------------
self.paths_H = util.get_image_paths(opt['dataroot_H']) # return None if input is None
self.count = 0
def __init__(self, opt):
super(DatasetDnPatch, self).__init__()
print(
'Get L/H for denosing on AWGN with fixed sigma. Only dataroot_H is needed.'
)
self.opt = opt
self.n_channels = opt['n_channels'] if opt['n_channels'] else 3
self.patch_size = opt['H_size'] if opt['H_size'] else 64
self.sigma = opt['sigma'] if opt['sigma'] else 25
self.sigma_test = opt['sigma_test'] if opt['sigma_test'] else self.sigma
self.num_patches_per_image = opt['num_patches_per_image'] if opt[
'num_patches_per_image'] else 40
self.num_sampled = opt['num_sampled'] if opt['num_sampled'] else 3000
# ------------------------------------
# get paths of H
# ------------------------------------
self.paths_H = util.get_image_paths(opt['dataroot_H'])
assert self.paths_H, 'Error: H path is empty.'
# ------------------------------------
# number of sampled H images
# ------------------------------------
self.num_sampled = min(self.num_sampled, len(self.paths_H))
# ------------------------------------
# reserve space with zeros
# ------------------------------------
self.total_patches = self.num_sampled * self.num_patches_per_image
self.H_data = np.zeros([
self.total_patches, self.patch_size, self.patch_size,
self.n_channels
],
dtype=np.uint8)
# ------------------------------------
# update H patches
# ------------------------------------
self.update_data()
def main():
# ----------------------------------------
# Preparation
# ----------------------------------------
if noise_level_model == -1:
model_name = 'srmdnf_x' + str(sf)
else:
model_name = 'srmd_x' + str(sf)
model_path = os.path.join(model_pool, model_name+'.pth')
in_nc = 18 if 'nf' in model_name else 19
# ----------------------------------------
# L_path, E_path, H_path
# ----------------------------------------
L_path = sources # L_path, for Low-quality images
E_path = results # E_path, for Estimated images
if not os.path.splitext(E_path)[1]:
util.mkdir(E_path)
device = torch.device(using_device)
# ----------------------------------------
# load model
# ----------------------------------------
from utils.network_srmd import SRMD as net
model = net(in_nc=in_nc, out_nc=n_channels, nc=nc, nb=nb,
upscale=sf, act_mode='R', upsample_mode='pixelshuffle')
model.load_state_dict(torch.load(model_path), strict=False)
model.eval()
for _, v in model.named_parameters():
v.requires_grad = False
model = model.to(device)
if os.path.isfile(L_path):
L_paths = [L_path]
else:
L_paths = util.get_image_paths(L_path)
# ----------------------------------------
# kernel and PCA reduced feature
# ----------------------------------------
# Gaussian kernel, delta kernel 0.01
kernel = utils_deblur.fspecial('gaussian', 15, 0.01)
P = loadmat(srmd_pca_path)['P']
degradation_vector = np.dot(P, np.reshape(kernel, (-1), order="F"))
if 'nf' not in model_name: # noise-free SR
degradation_vector = np.append(
degradation_vector, noise_level_model/255.)
degradation_vector = torch.from_numpy(
degradation_vector).view(1, -1, 1, 1).float()
for _, img in enumerate(L_paths):
img_name, _ = os.path.splitext(os.path.basename(img))
try:
# ------------------------------------
# (1) img_L
# ------------------------------------
img_L, alpha = util.imread_uint_alpha(img, n_channels=n_channels)
# Bicubic to handle alpha channel if the intended picture is supposed to have.
if not alpha is None and picture_format == "png":
alpha = util.uint2tensor4(alpha)
alpha = torch.nn.functional.interpolate(
alpha, scale_factor=sf, mode='bicubic', align_corners=False)
alpha = alpha.to(device)
alpha = torch.clamp(alpha, 0, 255)
alpha = util.tensor2uint(alpha)
img_L = util.uint2tensor4(img_L)
degradation_map = degradation_vector.repeat(
1, 1, img_L.size(-2), img_L.size(-1))
img_L = torch.cat((img_L, degradation_map), dim=1)
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 not alpha is None and picture_format == "png":
alpha = alpha.reshape((alpha.shape[0], alpha.shape[1], 1))
img_E = np.concatenate((img_E, alpha), axis=2)
elif not alpha is None:
print("Warning! You lost your alpha channel for this picture!")
# ------------------------------------
# save results
# ------------------------------------
if os.path.splitext(E_path)[1]:
util.imsave(img_E, E_path)
else:
util.imsave(img_E, os.path.join(
E_path, img_name+'.' + picture_format))
print(os.path.basename(img) + " successfully saved to disk!")
except Exception:
traceback.print_exc()
print(os.path.basename(img) + " failed!")
def main():
# ----------------------------------------
# Preparation
# ----------------------------------------
noise_level_img = 0 / 255.0 # set AWGN noise level for LR image, default: 0
noise_level_model = noise_level_img # set noise level of model, default: 0
model_name = 'ircnn_color' # set denoiser, 'drunet_color' | 'ircnn_color'
testset_name = 'Set18' # set testing set, 'set18' | 'set24'
x8 = True # set PGSE to boost performance, default: True
iter_num = 40 # set number of iterations, default: 40 for demosaicing
modelSigma1 = 49 # set sigma_1, default: 49
modelSigma2 = max(0.6, noise_level_model * 255.) # set sigma_2, default
matlab_init = True
show_img = False # default: False
save_L = True # save LR image
save_E = True # save estimated image
save_LEH = False # save zoomed LR, E and H images
border = 10 # default 10 for demosaicing
task_current = 'dm' # 'dm' for demosaicing
n_channels = 3 # fixed
model_zoo = 'model_zoo' # fixed
testsets = 'testsets' # fixed
results = 'results' # fixed
result_name = testset_name + '_' + task_current + '_' + model_name
model_path = os.path.join(model_zoo, model_name + '.pth')
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
torch.cuda.empty_cache()
# ----------------------------------------
# L_path, E_path, H_path
# ----------------------------------------
L_path = os.path.join(testsets,
testset_name) # L_path, for Low-quality images
E_path = os.path.join(results, result_name) # E_path, for Estimated images
util.mkdir(E_path)
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)
# ----------------------------------------
# load model
# ----------------------------------------
if 'drunet' in model_name:
from models.network_unet import UNetRes as net
model = net(in_nc=n_channels + 1,
out_nc=n_channels,
nc=[64, 128, 256, 512],
nb=4,
act_mode='R',
downsample_mode="strideconv",
upsample_mode="convtranspose")
model.load_state_dict(torch.load(model_path), strict=True)
model.eval()
for _, v in model.named_parameters():
v.requires_grad = False
model = model.to(device)
elif 'ircnn' in model_name:
from models.network_dncnn import IRCNN as net
model = net(in_nc=n_channels, out_nc=n_channels, nc=64)
model25 = torch.load(model_path)
former_idx = 0
logger.info('model_name:{}, image sigma:{:.3f}, model sigma:{:.3f}'.format(
model_name, noise_level_img, noise_level_model))
logger.info('Model path: {:s}'.format(model_path))
logger.info(L_path)
L_paths = util.get_image_paths(L_path)
test_results = OrderedDict()
test_results['psnr'] = []
for idx, img in enumerate(L_paths):
# --------------------------------
# (1) get img_H and img_L
# --------------------------------
idx += 1
img_name, ext = os.path.splitext(os.path.basename(img))
img_H = util.imread_uint(img, n_channels=n_channels)
CFA, CFA4, mosaic, mask = utils_mosaic.mosaic_CFA_Bayer(img_H)
# --------------------------------
# (2) initialize x
# --------------------------------
if matlab_init: # matlab demosaicing for initialization
CFA4 = util.uint2tensor4(CFA4).to(device)
x = utils_mosaic.dm_matlab(CFA4)
else:
x = cv2.cvtColor(CFA, cv2.COLOR_BAYER_BG2RGB_EA)
x = util.uint2tensor4(x).to(device)
img_L = util.tensor2uint(x)
y = util.uint2tensor4(mosaic).to(device)
util.imshow(img_L) if show_img else None
mask = util.single2tensor4(mask.astype(np.float32)).to(device)
# --------------------------------
# (3) get rhos and sigmas
# --------------------------------
rhos, sigmas = pnp.get_rho_sigma(sigma=max(0.255 / 255.,
noise_level_img),
iter_num=iter_num,
modelSigma1=modelSigma1,
modelSigma2=modelSigma2,
w=1.0)
rhos, sigmas = torch.tensor(rhos).to(device), torch.tensor(sigmas).to(
device)
# --------------------------------
# (4) main iterations
# --------------------------------
for i in range(iter_num):
# --------------------------------
# step 1, closed-form solution
# --------------------------------
x = (y + rhos[i].float() * x).div(mask + rhos[i])
# --------------------------------
# step 2, denoiser
# --------------------------------
if 'ircnn' in model_name:
current_idx = np.int(
np.ceil(sigmas[i].cpu().numpy() * 255. / 2.) - 1)
if current_idx != former_idx:
model.load_state_dict(model25[str(current_idx)],
strict=True)
model.eval()
for _, v in model.named_parameters():
v.requires_grad = False
model = model.to(device)
former_idx = current_idx
x = torch.clamp(x, 0, 1)
if x8:
x = util.augment_img_tensor4(x, i % 8)
if 'drunet' in model_name:
x = torch.cat((x, sigmas[i].float().repeat(
1, 1, x.shape[2], x.shape[3])),
dim=1)
x = utils_model.test_mode(model,
x,
mode=2,
refield=32,
min_size=256,
modulo=16)
# x = model(x)
elif 'ircnn' in model_name:
x = model(x)
if x8:
if i % 8 == 3 or i % 8 == 5:
x = util.augment_img_tensor4(x, 8 - i % 8)
else:
x = util.augment_img_tensor4(x, i % 8)
x[mask.to(torch.bool)] = y[mask.to(torch.bool)]
# --------------------------------
# (4) img_E
# --------------------------------
img_E = util.tensor2uint(x)
psnr = util.calculate_psnr(img_E, img_H, border=border)
test_results['psnr'].append(psnr)
logger.info('{:->4d}--> {:>10s} -- PSNR: {:.2f}dB'.format(
idx, img_name + ext, psnr))
if save_E:
util.imsave(
img_E,
os.path.join(E_path, img_name + '_' + model_name + '.png'))
if save_L:
util.imsave(img_L, os.path.join(E_path, img_name + '_L.png'))
if save_LEH:
util.imsave(
np.concatenate([img_L, img_E, img_H], axis=1),
os.path.join(E_path, img_name + model_name + '_LEH.png'))
ave_psnr = sum(test_results['psnr']) / len(test_results['psnr'])
logger.info('------> Average PSNR(RGB) of ({}) is : {:.2f} dB'.format(
testset_name, ave_psnr))
def main():
# ----------------------------------------
# Preparation
# ----------------------------------------
noise_level_img = 0 # default: 0, noise level for LR image
noise_level_model = noise_level_img # noise level for model
model_name = 'srmdnf_x4' # 'srmd_x2' | 'srmd_x3' | 'srmd_x4' | 'srmdnf_x2' | 'srmdnf_x3' | 'srmdnf_x4'
testset_name = 'set5' # test set, 'set5' | 'srbsd68'
sf = [int(s) for s in re.findall(r'\d+', model_name)][0] # scale factor
x8 = False # default: False, x8 to boost performance
need_degradation = True # default: True, use degradation model to generate LR image
show_img = False # default: False
srmd_pca_path = os.path.join('kernels', 'srmd_pca_matlab.mat')
task_current = 'sr' # 'dn' for denoising | 'sr' for super-resolution
n_channels = 3 # fixed
in_nc = 18 if 'nf' in model_name else 19
nc = 128 # fixed, number of channels
nb = 12 # fixed, number of conv layers
model_pool = 'model_zoo' # fixed
testsets = 'testsets' # fixed
results = 'results' # fixed
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_srmd import SRMD as net
model = net(in_nc=in_nc,
out_nc=n_channels,
nc=nc,
nb=nb,
upscale=sf,
act_mode='R',
upsample_mode='pixelshuffle')
model.load_state_dict(torch.load(model_path), 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:{}, model sigma:{}, image sigma:{}'.format(
model_name, noise_level_img, noise_level_model))
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
# ----------------------------------------
# kernel and PCA reduced feature
# ----------------------------------------
# kernel = sr.anisotropic_Gaussian(ksize=15, theta=np.pi, l1=4, l2=4)
kernel = utils_deblur.fspecial('gaussian', 15,
0.01) # Gaussian kernel, delta kernel 0.01
P = loadmat(srmd_pca_path)['P']
degradation_vector = np.dot(P, np.reshape(kernel, (-1), order="F"))
if 'nf' not in model_name: # noise-free SR
degradation_vector = np.append(degradation_vector,
noise_level_model / 255.)
degradation_vector = torch.from_numpy(degradation_vector).view(
1, -1, 1, 1).float()
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, blur + bicubic downsampling + Gaussian noise
if need_degradation:
img_L = util.modcrop(img_L, sf)
img_L = sr.srmd_degradation(
img_L, kernel, sf
) # equivalent to bicubic degradation if kernel is a delta kernel
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)
degradation_map = degradation_vector.repeat(1, 1, img_L.size(-2),
img_L.size(-1))
img_L = torch.cat((img_L, degradation_map), dim=1)
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))
def main():
"""
# ----------------------------------------------------------------------------------
# In real applications, you should set proper
# - "noise_level_img": from [3, 25], set 3 for clean image, try 15 for very noisy LR images
# - "k" (or "kernel_width"): blur kernel is very important!!! kernel_width from [0.6, 3.0]
# to get the best performance.
# ----------------------------------------------------------------------------------
"""
##############################################################################
testset_name = 'Set3C' # set test set, 'set5' | 'srbsd68'
noise_level_img = 3 # set noise level of image, from [3, 25], set 3 for clean image
model_name = 'drunet_color' # 'ircnn_color' # set denoiser, | 'drunet_color' | 'ircnn_gray' | 'drunet_gray' | 'ircnn_color'
sf = 2 # set scale factor, 1, 2, 3, 4
iter_num = 24 # set number of iterations, default: 24 for SISR
# --------------------------------
# set blur kernel
# --------------------------------
kernel_width_default_x1234 = [
0.6, 0.9, 1.7, 2.2
] # Gaussian kernel widths for x1, x2, x3, x4
noise_level_model = noise_level_img / 255. # noise level of model
kernel_width = kernel_width_default_x1234[sf - 1]
"""
# set your own kernel width !!!!!!!!!!
"""
# kernel_width = 1.0
k = utils_deblur.fspecial('gaussian', 25, kernel_width)
k = sr.shift_pixel(k, sf) # shift the kernel
k /= np.sum(k)
##############################################################################
show_img = False
util.surf(k) if show_img else None
x8 = True # default: False, x8 to boost performance
modelSigma1 = 49 # set sigma_1, default: 49
modelSigma2 = max(sf, noise_level_model * 255.)
classical_degradation = True # set classical degradation or bicubic degradation
task_current = 'sr' # 'sr' for super-resolution
n_channels = 1 if 'gray' in model_name else 3 # fixed
model_zoo = 'model_zoo' # fixed
testsets = 'testsets' # fixed
results = 'results' # fixed
result_name = testset_name + '_realapplications_' + task_current + '_' + model_name
model_path = os.path.join(model_zoo, model_name + '.pth')
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
torch.cuda.empty_cache()
# ----------------------------------------
# L_path, E_path, H_path
# ----------------------------------------
L_path = os.path.join(testsets,
testset_name) # L_path, for Low-quality images
E_path = os.path.join(results, result_name) # E_path, for Estimated images
util.mkdir(E_path)
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)
# ----------------------------------------
# load model
# ----------------------------------------
if 'drunet' in model_name:
from models.network_unet import UNetRes as net
model = net(in_nc=n_channels + 1,
out_nc=n_channels,
nc=[64, 128, 256, 512],
nb=4,
act_mode='R',
downsample_mode="strideconv",
upsample_mode="convtranspose")
model.load_state_dict(torch.load(model_path), strict=True)
model.eval()
for _, v in model.named_parameters():
v.requires_grad = False
model = model.to(device)
elif 'ircnn' in model_name:
from models.network_dncnn import IRCNN as net
model = net(in_nc=n_channels, out_nc=n_channels, nc=64)
model25 = torch.load(model_path)
former_idx = 0
logger.info('model_name:{}, image sigma:{:.3f}, model sigma:{:.3f}'.format(
model_name, noise_level_img, noise_level_model))
logger.info('Model path: {:s}'.format(model_path))
logger.info(L_path)
L_paths = util.get_image_paths(L_path)
for idx, img in enumerate(L_paths):
# --------------------------------
# (1) get img_L
# --------------------------------
logger.info('Model path: {:s} Image: {:s}'.format(model_path, img))
img_name, ext = os.path.splitext(os.path.basename(img))
img_L = util.imread_uint(img, n_channels=n_channels)
img_L = util.uint2single(img_L)
img_L = util.modcrop(img_L, 8) # modcrop
# --------------------------------
# (2) get rhos and sigmas
# --------------------------------
rhos, sigmas = pnp.get_rho_sigma(sigma=max(0.255 / 255.,
noise_level_model),
iter_num=iter_num,
modelSigma1=modelSigma1,
modelSigma2=modelSigma2,
w=1)
rhos, sigmas = torch.tensor(rhos).to(device), torch.tensor(sigmas).to(
device)
# --------------------------------
# (3) initialize x, and pre-calculation
# --------------------------------
x = cv2.resize(img_L, (img_L.shape[1] * sf, img_L.shape[0] * sf),
interpolation=cv2.INTER_CUBIC)
if np.ndim(x) == 2:
x = x[..., None]
if classical_degradation:
x = sr.shift_pixel(x, sf)
x = util.single2tensor4(x).to(device)
img_L_tensor, k_tensor = util.single2tensor4(
img_L), util.single2tensor4(np.expand_dims(k, 2))
[k_tensor, img_L_tensor] = util.todevice([k_tensor, img_L_tensor],
device)
FB, FBC, F2B, FBFy = sr.pre_calculate(img_L_tensor, k_tensor, sf)
# --------------------------------
# (4) main iterations
# --------------------------------
for i in range(iter_num):
print('Iter: {} / {}'.format(i, iter_num))
# --------------------------------
# step 1, FFT
# --------------------------------
tau = rhos[i].float().repeat(1, 1, 1, 1)
x = sr.data_solution(x, FB, FBC, F2B, FBFy, tau, sf)
if 'ircnn' in model_name:
current_idx = np.int(
np.ceil(sigmas[i].cpu().numpy() * 255. / 2.) - 1)
if current_idx != former_idx:
model.load_state_dict(model25[str(current_idx)],
strict=True)
model.eval()
for _, v in model.named_parameters():
v.requires_grad = False
model = model.to(device)
former_idx = current_idx
# --------------------------------
# step 2, denoiser
# --------------------------------
if x8:
x = util.augment_img_tensor4(x, i % 8)
if 'drunet' in model_name:
x = torch.cat(
(x, sigmas[i].repeat(1, 1, x.shape[2], x.shape[3])), dim=1)
x = utils_model.test_mode(model,
x,
mode=2,
refield=64,
min_size=256,
modulo=16)
elif 'ircnn' in model_name:
x = model(x)
if x8:
if i % 8 == 3 or i % 8 == 5:
x = util.augment_img_tensor4(x, 8 - i % 8)
else:
x = util.augment_img_tensor4(x, i % 8)
# --------------------------------
# (3) img_E
# --------------------------------
img_E = util.tensor2uint(x)
util.imsave(
img_E,
os.path.join(E_path, img_name + '_x' + str(sf) + '_' + model_name +
'.png'))
def main():
# ----------------------------------------
# Preparation
# ----------------------------------------
model_name = 'usrnet' # 'usrgan' | 'usrnet' | 'usrgan_tiny' | 'usrnet_tiny'
testset_name = 'set5' # test set, 'set5' | 'srbsd68'
test_sf = [4] if 'gan' in model_name else [
2, 3, 4
] # scale factor, from {1,2,3,4}
show_img = False # default: False
save_L = True # save LR image
save_E = True # save estimated image
save_LEH = False # save zoomed LR, E and H images
# ----------------------------------------
# load testing kernels
# ----------------------------------------
# kernels = hdf5storage.loadmat(os.path.join('kernels', 'kernels.mat'))['kernels']
kernels = loadmat(os.path.join('kernels', 'kernels_12.mat'))['kernels']
n_channels = 1 if 'gray' in model_name else 3 # 3 for color image, 1 for grayscale image
model_pool = 'model_zoo' # fixed
testsets = 'testsets' # fixed
results = 'results' # fixed
noise_level_img = 0 # fixed: 0, noise level for LR image
noise_level_model = noise_level_img # fixed, noise level of model, default 0
result_name = testset_name + '_' + model_name
model_path = os.path.join(model_pool, model_name + '.pth')
# ----------------------------------------
# L_path = H_path, E_path, logger
# ----------------------------------------
L_path = os.path.join(
testsets,
testset_name) # L_path and H_path, fixed, for Low-quality images
E_path = os.path.join(results,
result_name) # E_path, fixed, for Estimated images
util.mkdir(E_path)
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)
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
# ----------------------------------------
# load model
# ----------------------------------------
if 'tiny' in model_name:
model = net(n_iter=6,
h_nc=32,
in_nc=4,
out_nc=3,
nc=[16, 32, 64, 64],
nb=2,
act_mode="R",
downsample_mode='strideconv',
upsample_mode="convtranspose")
else:
model = net(n_iter=8,
h_nc=64,
in_nc=4,
out_nc=3,
nc=[64, 128, 256, 512],
nb=2,
act_mode="R",
downsample_mode='strideconv',
upsample_mode="convtranspose")
model.load_state_dict(torch.load(model_path), strict=True)
model.eval()
for key, v in model.named_parameters():
v.requires_grad = False
number_parameters = sum(map(lambda x: x.numel(), model.parameters()))
model = model.to(device)
logger.info('Model path: {:s}'.format(model_path))
logger.info('Params number: {}'.format(number_parameters))
logger.info('Model_name:{}, image sigma:{}'.format(model_name,
noise_level_img))
logger.info(L_path)
L_paths = util.get_image_paths(L_path)
# --------------------------------
# read images
# --------------------------------
test_results_ave = OrderedDict()
test_results_ave['psnr_sf_k'] = []
for sf in test_sf:
for k_index in range(kernels.shape[1]):
test_results = OrderedDict()
test_results['psnr'] = []
kernel = kernels[0, k_index].astype(np.float64)
## other kernels
# kernel = utils_deblur.blurkernel_synthesis(h=25) # motion kernel
# kernel = utils_deblur.fspecial('gaussian', 25, 1.6) # Gaussian kernel
# kernel = sr.shift_pixel(kernel, sf) # pixel shift; optional
# kernel /= np.sum(kernel)
util.surf(kernel) if show_img else None
idx = 0
for img in L_paths:
# --------------------------------
# (1) classical degradation, img_L
# --------------------------------
idx += 1
img_name, ext = os.path.splitext(os.path.basename(img))
img_H = util.imread_uint(
img, n_channels=n_channels) # HR image, int8
img_H = util.modcrop(img_H, np.lcm(sf, 8)) # modcrop
# generate degraded LR image
img_L = ndimage.filters.convolve(img_H,
kernel[..., np.newaxis],
mode='wrap') # blur
img_L = sr.downsample_np(
img_L, sf,
center=False) # downsample, standard s-fold downsampler
img_L = util.uint2single(img_L) # uint2single
np.random.seed(seed=0) # for reproducibility
img_L += np.random.normal(0, noise_level_img,
img_L.shape) # add AWGN
util.imshow(util.single2uint(img_L)) if show_img else None
x = util.single2tensor4(img_L)
k = util.single2tensor4(kernel[..., np.newaxis])
sigma = torch.tensor(noise_level_model).float().view(
[1, 1, 1, 1])
[x, k, sigma] = [el.to(device) for el in [x, k, sigma]]
# --------------------------------
# (2) inference
# --------------------------------
x = model(x, k, sf, sigma)
# --------------------------------
# (3) img_E
# --------------------------------
img_E = util.tensor2uint(x)
if save_E:
util.imsave(
img_E,
os.path.join(
E_path, img_name + '_x' + str(sf) + '_k' +
str(k_index + 1) + '_' + model_name + '.png'))
# --------------------------------
# (4) img_LEH
# --------------------------------
img_L = util.single2uint(img_L)
if save_LEH:
k_v = kernel / np.max(kernel) * 1.2
k_v = util.single2uint(
np.tile(k_v[..., np.newaxis], [1, 1, 3]))
k_v = cv2.resize(k_v, (3 * k_v.shape[1], 3 * k_v.shape[0]),
interpolation=cv2.INTER_NEAREST)
img_I = cv2.resize(
img_L, (sf * img_L.shape[1], sf * img_L.shape[0]),
interpolation=cv2.INTER_NEAREST)
img_I[:k_v.shape[0], -k_v.shape[1]:, :] = k_v
img_I[:img_L.shape[0], :img_L.shape[1], :] = img_L
util.imshow(np.concatenate([img_I, img_E, img_H], axis=1),
title='LR / Recovered / Ground-truth'
) if show_img else None
util.imsave(
np.concatenate([img_I, img_E, img_H], axis=1),
os.path.join(
E_path, img_name + '_x' + str(sf) + '_k' +
str(k_index + 1) + '_LEH.png'))
if save_L:
util.imsave(
img_L,
os.path.join(
E_path, img_name + '_x' + str(sf) + '_k' +
str(k_index + 1) + '_LR.png'))
psnr = util.calculate_psnr(
img_E, img_H, border=sf**2) # change with your own border
test_results['psnr'].append(psnr)
logger.info(
'{:->4d}--> {:>10s} -- x{:>2d} --k{:>2d} PSNR: {:.2f}dB'.
format(idx, img_name + ext, sf, k_index, psnr))
ave_psnr_k = sum(test_results['psnr']) / len(test_results['psnr'])
logger.info(
'------> Average PSNR(RGB) of ({}) scale factor: ({}), kernel: ({}) sigma: ({}): {:.2f} dB'
.format(testset_name, sf, k_index + 1, noise_level_model,
ave_psnr_k))
test_results_ave['psnr_sf_k'].append(ave_psnr_k)
logger.info(test_results_ave['psnr_sf_k'])
def main():
utils_logger.logger_info('AIM-track', log_path='AIM-track.log')
logger = logging.getLogger('AIM-track')
# --------------------------------
# basic settings
# --------------------------------
testsets = 'DIV2K'
testset_L = 'DIV2K_valid_LR_bicubic'
#testset_L = 'DIV2K_test_LR_bicubic'
torch.cuda.current_device()
torch.cuda.empty_cache()
#torch.backends.cudnn.benchmark = True
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
# --------------------------------
# load model
# --------------------------------
model_path = os.path.join('trained_model', 'RFDN_AIM.pth')
model = RFDN()
model.load_state_dict(torch.load(model_path), strict=True)
model.eval()
for k, v in model.named_parameters():
v.requires_grad = False
model = model.to(device)
# number of parameters
number_parameters = sum(map(lambda x: x.numel(), model.parameters()))
logger.info('Params number: {}'.format(number_parameters))
# --------------------------------
# read image
# --------------------------------
L_folder = os.path.join(testsets, testset_L, 'X4')
E_folder = os.path.join(testsets, testset_L+'_results')
util.mkdir(E_folder)
# record PSNR, runtime
test_results = OrderedDict()
test_results['runtime'] = []
logger.info(L_folder)
logger.info(E_folder)
idx = 0
start = torch.cuda.Event(enable_timing=True)
end = torch.cuda.Event(enable_timing=True)
img_SR = []
for img in util.get_image_paths(L_folder):
# --------------------------------
# (1) img_L
# --------------------------------
idx += 1
img_name, ext = os.path.splitext(os.path.basename(img))
logger.info('{:->4d}--> {:>10s}'.format(idx, img_name+ext))
img_L = util.imread_uint(img, n_channels=3)
img_L = util.uint2tensor4(img_L)
img_L = img_L.to(device)
start.record()
img_E = model(img_L)
end.record()
torch.cuda.synchronize()
test_results['runtime'].append(start.elapsed_time(end)) # milliseconds
# --------------------------------
# (2) img_E
# --------------------------------
img_E = util.tensor2uint(img_E)
img_SR.append(img_E)
# --------------------------------
# (3) save results
# --------------------------------
#util.imsave(img_E, os.path.join(E_folder, img_name+ext))
ave_runtime = sum(test_results['runtime']) / len(test_results['runtime']) / 1000.0
logger.info('------> Average runtime of ({}) is : {:.6f} seconds'.format(L_folder, ave_runtime))
# --------------------------------
# (4) calculate psnr
# --------------------------------
'''
def main():
# ----------------------------------------
# Preparation
# ----------------------------------------
noise_level_img = 15 # set AWGN noise level for noisy image
noise_level_model = noise_level_img # set noise level for model
model_name = 'drunet_gray' # set denoiser model, 'drunet_gray' | 'drunet_color'
testset_name = 'bsd68' # set test set, 'bsd68' | 'cbsd68' | 'set12'
x8 = False # default: False, x8 to boost performance
show_img = False # default: False
border = 0 # shave boader to calculate PSNR and SSIM
if 'color' in model_name:
n_channels = 3 # 3 for color image
else:
n_channels = 1 # 1 for grayscale image
model_pool = 'model_zoo' # fixed
testsets = 'testsets' # fixed
results = 'results' # fixed
task_current = 'dn' # 'dn' for denoising
result_name = testset_name + '_' + task_current + '_' + model_name
model_path = os.path.join(model_pool, model_name + '.pth')
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
torch.cuda.empty_cache()
# ----------------------------------------
# L_path, E_path, H_path
# ----------------------------------------
L_path = os.path.join(testsets,
testset_name) # L_path, for Low-quality images
E_path = os.path.join(results, result_name) # E_path, for Estimated images
util.mkdir(E_path)
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)
# ----------------------------------------
# load model
# ----------------------------------------
from models.network_unet import UNetRes as net
model = net(in_nc=n_channels + 1,
out_nc=n_channels,
nc=[64, 128, 256, 512],
nb=4,
act_mode='R',
downsample_mode="strideconv",
upsample_mode="convtranspose")
model.load_state_dict(torch.load(model_path), strict=True)
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'] = []
logger.info('model_name:{}, model sigma:{}, image sigma:{}'.format(
model_name, noise_level_img, noise_level_model))
logger.info(L_path)
L_paths = util.get_image_paths(L_path)
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_H = util.imread_uint(img, n_channels=n_channels)
img_L = util.uint2single(img_H)
# Add noise without clipping
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='Noisy image with noise level {}'.format(
noise_level_img)) if show_img else None
img_L = util.single2tensor4(img_L)
img_L = torch.cat(
(img_L, torch.FloatTensor([noise_level_model / 255.]).repeat(
1, 1, img_L.shape[2], img_L.shape[3])),
dim=1)
img_L = img_L.to(device)
# ------------------------------------
# (2) img_E
# ------------------------------------
if not x8 and img_L.size(2) // 8 == 0 and img_L.size(3) // 8 == 0:
img_E = model(img_L)
elif not x8 and (img_L.size(2) // 8 != 0 or img_L.size(3) // 8 != 0):
img_E = utils_model.test_mode(model, img_L, refield=64, mode=5)
elif x8:
img_E = utils_model.test_mode(model, img_L, mode=3)
img_E = util.tensor2uint(img_E)
# --------------------------------
# PSNR and SSIM
# --------------------------------
if n_channels == 1:
img_H = img_H.squeeze()
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))
# ------------------------------------
# save results
# ------------------------------------
util.imsave(img_E, os.path.join(E_path, img_name + ext))
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) - {} - PSNR: {:.2f} dB; SSIM: {:.4f}'.format(
result_name, ave_psnr, ave_ssim))
def main():
# ----------------------------------------
# Preparation
# ----------------------------------------
noise_level_img = 0/255.0 # set AWGN noise level for LR image, default: 0,
noise_level_model = noise_level_img # setnoise level of model, default 0
model_name = 'drunet_color' # set denoiser, | 'drunet_color' | 'ircnn_gray' | 'drunet_gray' | 'ircnn_color'
testset_name = 'srbsd68' # set test set, 'set5' | 'srbsd68'
x8 = True # default: False, x8 to boost performance
test_sf = [2] # set scale factor, default: [2, 3, 4], [2], [3], [4]
iter_num = 24 # set number of iterations, default: 24 for SISR
modelSigma1 = 49 # set sigma_1, default: 49
classical_degradation = True # set classical degradation or bicubic degradation
show_img = False # default: False
save_L = True # save LR image
save_E = True # save estimated image
save_LEH = False # save zoomed LR, E and H images
task_current = 'sr' # 'sr' for super-resolution
n_channels = 1 if 'gray' in model_name else 3 # fixed
model_zoo = 'model_zoo' # fixed
testsets = 'testsets' # fixed
results = 'results' # fixed
result_name = testset_name + '_' + task_current + '_' + model_name
model_path = os.path.join(model_zoo, model_name+'.pth')
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
torch.cuda.empty_cache()
# ----------------------------------------
# L_path, E_path, H_path
# ----------------------------------------
L_path = os.path.join(testsets, testset_name) # L_path, for Low-quality images
E_path = os.path.join(results, result_name) # E_path, for Estimated images
util.mkdir(E_path)
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)
# ----------------------------------------
# load model
# ----------------------------------------
if 'drunet' in model_name:
from models.network_unet import UNetRes as net
model = net(in_nc=n_channels+1, out_nc=n_channels, nc=[64, 128, 256, 512], nb=4, act_mode='R', downsample_mode="strideconv", upsample_mode="convtranspose")
model.load_state_dict(torch.load(model_path), strict=True)
model.eval()
for _, v in model.named_parameters():
v.requires_grad = False
model = model.to(device)
elif 'ircnn' in model_name:
from models.network_dncnn import IRCNN as net
model = net(in_nc=n_channels, out_nc=n_channels, nc=64)
model25 = torch.load(model_path)
former_idx = 0
logger.info('model_name:{}, image sigma:{:.3f}, model sigma:{:.3f}'.format(model_name, noise_level_img, noise_level_model))
logger.info('Model path: {:s}'.format(model_path))
logger.info(L_path)
L_paths = util.get_image_paths(L_path)
# --------------------------------
# load kernel
# --------------------------------
# kernels = hdf5storage.loadmat(os.path.join('kernels', 'Levin09.mat'))['kernels']
if classical_degradation:
kernels = hdf5storage.loadmat(os.path.join('kernels', 'kernels_12.mat'))['kernels']
else:
kernels = hdf5storage.loadmat(os.path.join('kernels', 'kernel_bicubicx234.mat'))['kernels']
test_results_ave = OrderedDict()
test_results_ave['psnr_sf_k'] = []
test_results_ave['psnr_y_sf_k'] = []
for sf in test_sf:
border = sf
modelSigma2 = max(sf, noise_level_model*255.)
k_num = 8 if classical_degradation else 1
for k_index in range(k_num):
logger.info('--------- sf:{:>1d} --k:{:>2d} ---------'.format(sf, k_index))
test_results = OrderedDict()
test_results['psnr'] = []
test_results['psnr_y'] = []
if not classical_degradation: # for bicubic degradation
k_index = sf-2
k = kernels[0, k_index].astype(np.float64)
util.surf(k) if show_img else None
for idx, img in enumerate(L_paths):
# --------------------------------
# (1) get img_L
# --------------------------------
img_name, ext = os.path.splitext(os.path.basename(img))
img_H = util.imread_uint(img, n_channels=n_channels)
img_H = util.modcrop(img_H, sf) # modcrop
if classical_degradation:
img_L = sr.classical_degradation(img_H, k, sf)
util.imshow(img_L) if show_img else None
img_L = util.uint2single(img_L)
else:
img_L = util.imresize_np(util.uint2single(img_H), 1/sf)
np.random.seed(seed=0) # for reproducibility
img_L += np.random.normal(0, noise_level_img, img_L.shape) # add AWGN
# --------------------------------
# (2) get rhos and sigmas
# --------------------------------
rhos, sigmas = pnp.get_rho_sigma(sigma=max(0.255/255., noise_level_model), iter_num=iter_num, modelSigma1=modelSigma1, modelSigma2=modelSigma2, w=1)
rhos, sigmas = torch.tensor(rhos).to(device), torch.tensor(sigmas).to(device)
# --------------------------------
# (3) initialize x, and pre-calculation
# --------------------------------
x = cv2.resize(img_L, (img_L.shape[1]*sf, img_L.shape[0]*sf), interpolation=cv2.INTER_CUBIC)
if np.ndim(x)==2:
x = x[..., None]
if classical_degradation:
x = sr.shift_pixel(x, sf)
x = util.single2tensor4(x).to(device)
img_L_tensor, k_tensor = util.single2tensor4(img_L), util.single2tensor4(np.expand_dims(k, 2))
[k_tensor, img_L_tensor] = util.todevice([k_tensor, img_L_tensor], device)
FB, FBC, F2B, FBFy = sr.pre_calculate(img_L_tensor, k_tensor, sf)
# --------------------------------
# (4) main iterations
# --------------------------------
for i in range(iter_num):
# --------------------------------
# step 1, FFT
# --------------------------------
tau = rhos[i].float().repeat(1, 1, 1, 1)
x = sr.data_solution(x.float(), FB, FBC, F2B, FBFy, tau, sf)
if 'ircnn' in model_name:
current_idx = np.int(np.ceil(sigmas[i].cpu().numpy()*255./2.)-1)
if current_idx != former_idx:
model.load_state_dict(model25[str(current_idx)], strict=True)
model.eval()
for _, v in model.named_parameters():
v.requires_grad = False
model = model.to(device)
former_idx = current_idx
# --------------------------------
# step 2, denoiser
# --------------------------------
if x8:
x = util.augment_img_tensor4(x, i % 8)
if 'drunet' in model_name:
x = torch.cat((x, sigmas[i].float().repeat(1, 1, x.shape[2], x.shape[3])), dim=1)
x = utils_model.test_mode(model, x, mode=2, refield=32, min_size=256, modulo=16)
elif 'ircnn' in model_name:
x = model(x)
if x8:
if i % 8 == 3 or i % 8 == 5:
x = util.augment_img_tensor4(x, 8 - i % 8)
else:
x = util.augment_img_tensor4(x, i % 8)
# --------------------------------
# (3) img_E
# --------------------------------
img_E = util.tensor2uint(x)
if save_E:
util.imsave(img_E, os.path.join(E_path, img_name+'_x'+str(sf)+'_k'+str(k_index)+'_'+model_name+'.png'))
if n_channels == 1:
img_H = img_H.squeeze()
# --------------------------------
# (4) img_LEH
# --------------------------------
img_L = util.single2uint(img_L).squeeze()
if save_LEH:
k_v = k/np.max(k)*1.0
if n_channels==1:
k_v = util.single2uint(k_v)
else:
k_v = util.single2uint(np.tile(k_v[..., np.newaxis], [1, 1, n_channels]))
k_v = cv2.resize(k_v, (3*k_v.shape[1], 3*k_v.shape[0]), interpolation=cv2.INTER_NEAREST)
img_I = cv2.resize(img_L, (sf*img_L.shape[1], sf*img_L.shape[0]), interpolation=cv2.INTER_NEAREST)
img_I[:k_v.shape[0], -k_v.shape[1]:, ...] = k_v
img_I[:img_L.shape[0], :img_L.shape[1], ...] = img_L
util.imshow(np.concatenate([img_I, img_E, img_H], axis=1), title='LR / Recovered / Ground-truth') if show_img else None
util.imsave(np.concatenate([img_I, img_E, img_H], axis=1), os.path.join(E_path, img_name+'_x'+str(sf)+'_k'+str(k_index)+'_LEH.png'))
if save_L:
util.imsave(img_L, os.path.join(E_path, img_name+'_x'+str(sf)+'_k'+str(k_index)+'_LR.png'))
psnr = util.calculate_psnr(img_E, img_H, border=border)
test_results['psnr'].append(psnr)
logger.info('{:->4d}--> {:>10s} -- sf:{:>1d} --k:{:>2d} PSNR: {:.2f}dB'.format(idx+1, img_name+ext, sf, k_index, psnr))
if n_channels == 3:
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)
test_results['psnr_y'].append(psnr_y)
# --------------------------------
# Average PSNR for all kernels
# --------------------------------
ave_psnr_k = sum(test_results['psnr']) / len(test_results['psnr'])
logger.info('------> Average PSNR(RGB) of ({}) scale factor: ({}), kernel: ({}) sigma: ({:.2f}): {:.2f} dB'.format(testset_name, sf, k_index, noise_level_model, ave_psnr_k))
test_results_ave['psnr_sf_k'].append(ave_psnr_k)
if n_channels == 3: # RGB image
ave_psnr_y_k = sum(test_results['psnr_y']) / len(test_results['psnr_y'])
logger.info('------> Average PSNR(Y) of ({}) scale factor: ({}), kernel: ({}) sigma: ({:.2f}): {:.2f} dB'.format(testset_name, sf, k_index, noise_level_model, ave_psnr_y_k))
test_results_ave['psnr_y_sf_k'].append(ave_psnr_y_k)
# ---------------------------------------
# Average PSNR for all sf and kernels
# ---------------------------------------
ave_psnr_sf_k = sum(test_results_ave['psnr_sf_k']) / len(test_results_ave['psnr_sf_k'])
logger.info('------> Average PSNR of ({}) {:.2f} dB'.format(testset_name, ave_psnr_sf_k))
if n_channels == 3:
ave_psnr_y_sf_k = sum(test_results_ave['psnr_y_sf_k']) / len(test_results_ave['psnr_y_sf_k'])
logger.info('------> Average PSNR of ({}) {:.2f} dB'.format(testset_name, ave_psnr_y_sf_k))
model_name = 'dncnn_25'
sigma = 25
testset_name = 'bsd68'
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
criterion = nn.MSELoss(reduction='sum')
lr = 1e-5
epochs = 100
test_results = OrderedDict()
test_results['psnr_before'] = []
test_results['psnr_after'] = []
model_path = os.path.join(model_pool, model_name + '.pth')
test_paths = os.path.join(testsets, testset_name)
test_paths = util.get_image_paths(test_paths)
# training loop
for idx, img in enumerate(test_paths):
start_time = time.time()
# load model
model = DnCNN(in_nc=n_channels,
out_nc=n_channels,
nc=64,
nb=17,
act_mode='R')
model.load_state_dict(torch.load(model_path), strict=True)
model = model.to(device)
model.eval()
def main():
# ----------------------------------------
# Preparation
# ----------------------------------------
model_name = 'dncnn3' # 'dncnn3'- can be used for blind Gaussian denoising, JPEG deblocking (quality factor 5-100) and super-resolution (x234)
# important!
testset_name = 'bsd68' # test set, low-quality grayscale/color JPEG images
n_channels = 1 # set 1 for grayscale image, set 3 for color image
x8 = False # default: False, x8 to boost performance
testsets = 'testsets' # fixed
results = 'results' # fixed
result_name = testset_name + '_' + model_name # fixed
L_path = os.path.join(
testsets, testset_name
) # L_path, for Low-quality grayscale/Y-channel JPEG images
E_path = os.path.join(results, result_name) # E_path, for Estimated images
util.mkdir(E_path)
model_pool = 'model_zoo' # fixed
model_path = os.path.join(model_pool, model_name + '.pth')
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)
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
# ----------------------------------------
# load model
# ----------------------------------------
from models.network_dncnn import DnCNN as net
model = net(in_nc=1, out_nc=1, nc=64, nb=20, act_mode='R')
model.load_state_dict(torch.load(model_path), strict=True)
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))
logger.info(L_path)
L_paths = util.get_image_paths(L_path)
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)
if n_channels == 3:
ycbcr = util.rgb2ycbcr(img_L, False)
img_L = ycbcr[..., 0:1]
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)
img_E = util.tensor2single(img_E)
if n_channels == 3:
ycbcr[..., 0] = img_E
img_E = util.ycbcr2rgb(ycbcr)
img_E = util.single2uint(img_E)
# ------------------------------------
# save results
# ------------------------------------
util.imsave(img_E, os.path.join(E_path, img_name + '.png'))
def main(model=None, model_path=None):
utils_logger.logger_info('AIM-track',
log_path=os.path.join(model_path,
'AIM-track.log'))
logger = logging.getLogger('AIM-track')
# --------------------------------
# basic settings
# --------------------------------
testsets = 'DIV2K' # DIV2K root path
testset_L = 'DIV2K_test_LR_bicubic' # test image folder name
torch.cuda.current_device()
torch.cuda.empty_cache()
torch.backends.cudnn.benchmark = True
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
# --------------------------------
# load model
# --------------------------------
# model_path = os.path.join('MSRResNetx4_model', 'MSRResNetx4.pth')
if model is None:
model_path = 'MSRResNetx4_model'
model = MSRResNet(in_nc=3, out_nc=3, nf=64, nb=16, upscale=4)
model.load_state_dict(torch.load(os.path.join(model_path,
'model.pth')),
strict=True)
model.eval()
""" for k, v in model.named_parameters():
v.requires_grad = False
model = model.to(device) """
# number of parameters
number_parameters = sum(map(lambda x: x.numel(), model.parameters()))
logger.info('Params number: {}'.format(number_parameters))
print('Params number: {}'.format(number_parameters))
# --------------------------------
# read image
# --------------------------------
L_folder = os.path.join(testsets, testset_L)
assert os.path.isdir(L_folder) # check the test images path
E_folder = os.path.join(model_path, 'results')
util.mkdir(E_folder)
# record PSNR, runtime
test_results = OrderedDict()
test_results['runtime'] = []
logger.info(L_folder)
logger.info(E_folder)
idx = 0
start = torch.cuda.Event(enable_timing=True)
end = torch.cuda.Event(enable_timing=True)
for img in util.get_image_paths(L_folder):
# --------------------------------
# (1) img_L
# --------------------------------
idx += 1
img_name, ext = os.path.splitext(os.path.basename(img))
logger.info('{:->4d}--> {:>10s}'.format(idx, img_name + ext))
img_L = util.imread_uint(img, n_channels=3)
img_L = util.uint2tensor4(img_L)
img_L = img_L.to(device)
start.record()
img_E = model(img_L)
end.record()
torch.cuda.synchronize()
test_results['runtime'].append(start.elapsed_time(end)) # milliseconds
# torch.cuda.synchronize()
# start = time.time()
# img_E = model(img_L)
# torch.cuda.synchronize()
# end = time.time()
# test_results['runtime'].append(end-start) # seconds
# --------------------------------
# (2) img_E
# --------------------------------
img_E = util.tensor2uint(img_E)
util.imsave(img_E, os.path.join(E_folder, img_name + ext))
ave_runtime = sum(test_results['runtime']) / len(
test_results['runtime']) / 1000.0
logger.info('------> Average runtime of ({}) is : {:.6f} seconds'.format(
L_folder, ave_runtime))
print('------> Average runtime of ({}) is : {:.6f} seconds'.format(
L_folder, ave_runtime))
def main():
utils_logger.logger_info('blind_sr_log', log_path='blind_sr_log.log')
logger = logging.getLogger('blind_sr_log')
# print(torch.__version__) # pytorch version
# print(torch.version.cuda) # cuda version
# print(torch.backends.cudnn.version()) # cudnn version
testsets = 'testsets' # fixed, set path of testsets
testset_Ls = ['RealSRSet'] # ['RealSRSet','DPED']
model_names = ['RRDB','ESRGAN','FSSR_DPED','FSSR_JPEG','RealSR_DPED','RealSR_JPEG']
model_names = ['BSRGAN']
save_results = True
sf = 4
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
for model_name in model_names:
model_path = os.path.join('model_zoo', model_name+'.pth') # set model path
logger.info('{:>16s} : {:s}'.format('Model Name', model_name))
# torch.cuda.set_device(0) # set GPU ID
logger.info('{:>16s} : {:<d}'.format('GPU ID', torch.cuda.current_device()))
torch.cuda.empty_cache()
# --------------------------------
# define network and load model
# --------------------------------
model = net(in_nc=3, out_nc=3, nf=64, nb=23, gc=32) # define network
# model_old = torch.load(model_path)
# state_dict = model.state_dict()
# for ((key, param),(key2, param2)) in zip(model_old.items(), state_dict.items()):
# state_dict[key2] = param
# model.load_state_dict(state_dict, strict=True)
model.load_state_dict(torch.load(model_path), strict=True)
model.eval()
for k, v in model.named_parameters():
v.requires_grad = False
model = model.to(device)
torch.cuda.empty_cache()
for testset_L in testset_Ls:
L_path = os.path.join(testsets, testset_L)
#E_path = os.path.join(testsets, testset_L+'_'+model_name)
E_path = os.path.join(testsets, testset_L+'_results_x'+str(sf))
util.mkdir(E_path)
logger.info('{:>16s} : {:s}'.format('Input Path', L_path))
logger.info('{:>16s} : {:s}'.format('Output Path', E_path))
idx = 0
for img in util.get_image_paths(L_path):
# --------------------------------
# (1) img_L
# --------------------------------
idx += 1
img_name, ext = os.path.splitext(os.path.basename(img))
logger.info('{:->4d} --> {:<s} --> x{:<d}--> {:<s}'.format(idx, model_name, sf, img_name+ext))
img_L = util.imread_uint(img, n_channels=3)
img_L = util.uint2tensor4(img_L)
img_L = img_L.to(device)
# --------------------------------
# (2) inference
# --------------------------------
img_E = model(img_L)
# --------------------------------
# (3) img_E
# --------------------------------
img_E = util.tensor2uint(img_E)
if save_results:
util.imsave(img_E, os.path.join(E_path, img_name+'_'+model_name+'.png'))
def main():
# ----------------------------------------
# Preparation
# ----------------------------------------
noise_level_img = 50 # noise level for noisy image
model_name = 'ircnn_gray' # 'ircnn_gray' | 'ircnn_color'
testset_name = 'set12' # test set, 'bsd68' | 'set12'
need_degradation = True # default: True
x8 = False # default: False, x8 to boost performance
show_img = False # default: False
current_idx = min(24, np.int(np.ceil(noise_level_img/2)-1)) # current_idx+1 th denoiser
task_current = 'dn' # fixed, 'dn' for denoising | 'sr' for super-resolution
sf = 1 # unused for denoising
if 'color' in model_name:
n_channels = 3 # fixed, 1 for grayscale image, 3 for color image
else:
n_channels = 1 # fixed for grayscale image
model_pool = 'model_zoo' # fixed
testsets = 'testsets' # fixed
results = 'results' # fixed
result_name = testset_name + '_' + model_name # fixed
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
# ----------------------------------------
model25 = torch.load(model_path)
from models.network_dncnn import IRCNN as net
model = net(in_nc=n_channels, out_nc=n_channels, nc=64)
model.load_state_dict(model25[str(current_idx)], strict=True)
model.eval()
for _, 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'] = []
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)
if need_degradation: # degradation process
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='Noisy 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)
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()
# --------------------------------
# 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
# ------------------------------------
# save results
# ------------------------------------
util.imsave(img_E, os.path.join(E_path, img_name+ext))
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) - {} - PSNR: {:.2f} dB; SSIM: {:.4f}'.format(result_name, ave_psnr, ave_ssim))
def main():
# ----------------------------------------
# Preparation
# ----------------------------------------
noise_level_img = 30 # noise level for noisy image
noise_level_model = noise_level_img # noise level for model
model_name = 'ffdnet_color' # 'ffdnet_gray' | 'ffdnet_color' | 'ffdnet_color_clip' | 'ffdnet_gray_clip'
testset_name = 'CBSD68' # test set, 'bsd68' | 'cbsd68' | 'set12'
need_degradation = True # default: True
show_img = False # default: False
task_current = 'dn' # 'dn' for denoising | 'sr' for super-resolution
sf = 1 # unused for denoising
if 'color' in model_name:
n_channels = 3 # setting for color image
nc = 96 # setting for color image
nb = 12 # setting for color image
else:
n_channels = 1 # setting for grayscale image
nc = 64 # setting for grayscale image
nb = 15 # setting for grayscale image
if 'clip' in model_name:
use_clip = True # clip the intensities into range of [0, 1]
else:
use_clip = False
model_pool = 'model_zoo' # fixed
testsets = 'testsets' # fixed
results = 'results' # fixed
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_ffdnet import FFDNet as net
model = net(in_nc=n_channels,
out_nc=n_channels,
nc=nc,
nb=nb,
act_mode='R')
model.load_state_dict(torch.load(model_path), strict=True)
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))
test_results = OrderedDict()
test_results['psnr'] = []
test_results['ssim'] = []
logger.info('model_name:{}, model sigma:{}, image sigma:{}'.format(
model_name, noise_level_img, noise_level_model))
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)
if need_degradation: # degradation process
np.random.seed(seed=0) # for reproducibility
img_L += np.random.normal(0, noise_level_img / 255., img_L.shape)
if use_clip:
img_L = util.uint2single(util.single2uint(img_L))
util.imshow(util.single2uint(img_L),
title='Noisy 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)
sigma = torch.full((1, 1, 1, 1),
noise_level_model / 255.).type_as(img_L)
# ------------------------------------
# (2) img_E
# ------------------------------------
img_E = model(img_L, sigma)
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()
# --------------------------------
# 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
# ------------------------------------
# save results
# ------------------------------------
util.imsave(img_E, os.path.join(E_path, img_name + ext))
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) - {} - PSNR: {:.2f} dB; SSIM: {:.4f}'.
format(result_name, ave_psnr, ave_ssim))
def main():
# ----------------------------------------
# Preparation
# ----------------------------------------
noise_level_img = 7.65 / 255.0 # default: 0, noise level for LR image
noise_level_model = noise_level_img # noise level of model, default 0
model_name = 'drunet_gray' # 'drunet_gray' | 'drunet_color' | 'ircnn_gray' | 'ircnn_color'
testset_name = 'Set3C' # test set, 'set5' | 'srbsd68'
x8 = True # default: False, x8 to boost performance
iter_num = 8 # number of iterations
modelSigma1 = 49
modelSigma2 = noise_level_model * 255.
show_img = False # default: False
save_L = True # save LR image
save_E = True # save estimated image
save_LEH = False # save zoomed LR, E and H images
border = 0
# --------------------------------
# load kernel
# --------------------------------
kernels = hdf5storage.loadmat(os.path.join('kernels',
'Levin09.mat'))['kernels']
sf = 1
task_current = 'deblur' # 'deblur' for deblurring
n_channels = 3 if 'color' in model_name else 1 # fixed
model_zoo = 'model_zoo' # fixed
testsets = 'testsets' # fixed
results = 'results' # fixed
result_name = testset_name + '_' + task_current + '_' + model_name
model_path = os.path.join(model_zoo, model_name + '.pth')
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
torch.cuda.empty_cache()
# ----------------------------------------
# L_path, E_path, H_path
# ----------------------------------------
L_path = os.path.join(testsets,
testset_name) # L_path, for Low-quality images
E_path = os.path.join(results, result_name) # E_path, for Estimated images
util.mkdir(E_path)
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)
# ----------------------------------------
# load model
# ----------------------------------------
if 'drunet' in model_name:
from models.network_unet import UNetRes as net
model = net(in_nc=n_channels + 1,
out_nc=n_channels,
nc=[64, 128, 256, 512],
nb=4,
act_mode='R',
downsample_mode="strideconv",
upsample_mode="convtranspose")
model.load_state_dict(torch.load(model_path), strict=True)
model.eval()
for _, v in model.named_parameters():
v.requires_grad = False
model = model.to(device)
elif 'ircnn' in model_name:
from models.network_dncnn import IRCNN as net
model = net(in_nc=n_channels, out_nc=n_channels, nc=64)
model25 = torch.load(model_path)
former_idx = 0
logger.info('model_name:{}, image sigma:{:.3f}, model sigma:{:.3f}'.format(
model_name, noise_level_img, noise_level_model))
logger.info('Model path: {:s}'.format(model_path))
logger.info(L_path)
L_paths = util.get_image_paths(L_path)
test_results_ave = OrderedDict()
test_results_ave['psnr'] = [] # record average PSNR for each kernel
for k_index in range(kernels.shape[1]):
logger.info('-------k:{:>2d} ---------'.format(k_index))
test_results = OrderedDict()
test_results['psnr'] = []
k = kernels[0, k_index].astype(np.float64)
util.imshow(k) if show_img else None
for idx, img in enumerate(L_paths):
# --------------------------------
# (1) get img_L
# --------------------------------
img_name, ext = os.path.splitext(os.path.basename(img))
img_H = util.imread_uint(img, n_channels=n_channels)
img_H = util.modcrop(img_H, 8) # modcrop
img_L = ndimage.filters.convolve(img_H,
np.expand_dims(k, axis=2),
mode='wrap')
util.imshow(img_L) if show_img else None
img_L = util.uint2single(img_L)
np.random.seed(seed=0) # for reproducibility
img_L += np.random.normal(0, noise_level_img,
img_L.shape) # add AWGN
# --------------------------------
# (2) get rhos and sigmas
# --------------------------------
rhos, sigmas = pnp.get_rho_sigma(sigma=max(0.255 / 255.,
noise_level_model),
iter_num=iter_num,
modelSigma1=modelSigma1,
modelSigma2=modelSigma2,
w=1.0)
rhos, sigmas = torch.tensor(rhos).to(device), torch.tensor(
sigmas).to(device)
# --------------------------------
# (3) initialize x, and pre-calculation
# --------------------------------
x = util.single2tensor4(img_L).to(device)
img_L_tensor, k_tensor = util.single2tensor4(
img_L), util.single2tensor4(np.expand_dims(k, 2))
[k_tensor, img_L_tensor] = util.todevice([k_tensor, img_L_tensor],
device)
FB, FBC, F2B, FBFy = sr.pre_calculate(img_L_tensor, k_tensor, sf)
# --------------------------------
# (4) main iterations
# --------------------------------
for i in range(iter_num):
# --------------------------------
# step 1, FFT
# --------------------------------
tau = rhos[i].float().repeat(1, 1, 1, 1)
x = sr.data_solution(x, FB, FBC, F2B, FBFy, tau, sf)
if 'ircnn' in model_name:
current_idx = np.int(
np.ceil(sigmas[i].cpu().numpy() * 255. / 2.) - 1)
if current_idx != former_idx:
model.load_state_dict(model25[str(current_idx)],
strict=True)
model.eval()
for _, v in model.named_parameters():
v.requires_grad = False
model = model.to(device)
former_idx = current_idx
# --------------------------------
# step 2, denoiser
# --------------------------------
if x8:
x = util.augment_img_tensor4(x, i % 8)
if 'drunet' in model_name:
x = torch.cat((x, sigmas[i].float().repeat(
1, 1, x.shape[2], x.shape[3])),
dim=1)
x = utils_model.test_mode(model,
x,
mode=2,
refield=32,
min_size=256,
modulo=16)
elif 'ircnn' in model_name:
x = model(x)
if x8:
if i % 8 == 3 or i % 8 == 5:
x = util.augment_img_tensor4(x, 8 - i % 8)
else:
x = util.augment_img_tensor4(x, i % 8)
# --------------------------------
# (3) img_E
# --------------------------------
img_E = util.tensor2uint(x)
if n_channels == 1:
img_H = img_H.squeeze()
if save_E:
util.imsave(
img_E,
os.path.join(
E_path, img_name + '_k' + str(k_index) + '_' +
model_name + '.png'))
# --------------------------------
# (4) img_LEH
# --------------------------------
if save_LEH:
img_L = util.single2uint(img_L)
k_v = k / np.max(k) * 1.0
k_v = util.single2uint(np.tile(k_v[..., np.newaxis],
[1, 1, 3]))
k_v = cv2.resize(k_v, (3 * k_v.shape[1], 3 * k_v.shape[0]),
interpolation=cv2.INTER_NEAREST)
img_I = cv2.resize(img_L,
(sf * img_L.shape[1], sf * img_L.shape[0]),
interpolation=cv2.INTER_NEAREST)
img_I[:k_v.shape[0], -k_v.shape[1]:, :] = k_v
img_I[:img_L.shape[0], :img_L.shape[1], :] = img_L
util.imshow(np.concatenate([img_I, img_E, img_H], axis=1),
title='LR / Recovered / Ground-truth'
) if show_img else None
util.imsave(
np.concatenate([img_I, img_E, img_H], axis=1),
os.path.join(E_path,
img_name + '_k' + str(k_index) + '_LEH.png'))
if save_L:
util.imsave(
util.single2uint(img_L),
os.path.join(E_path,
img_name + '_k' + str(k_index) + '_LR.png'))
psnr = util.calculate_psnr(
img_E, img_H, border=border) # change with your own border
test_results['psnr'].append(psnr)
logger.info('{:->4d}--> {:>10s} --k:{:>2d} PSNR: {:.2f}dB'.format(
idx + 1, img_name + ext, k_index, psnr))
# --------------------------------
# Average PSNR
# --------------------------------
ave_psnr = sum(test_results['psnr']) / len(test_results['psnr'])
logger.info(
'------> Average PSNR of ({}), kernel: ({}) sigma: ({:.2f}): {:.2f} dB'
.format(testset_name, k_index, noise_level_model, ave_psnr))
test_results_ave['psnr'].append(ave_psnr)
def main():
# ----------------------------------------
# Preparation
# ----------------------------------------
model_name = 'usrnet' # 'usrgan' | 'usrnet' | 'usrgan_tiny' | 'usrnet_tiny'
testset_name = 'set5' # test set, 'set5' | 'srbsd68'
need_degradation = True # default: True
sf = 4 # scale factor, only from {2, 3, 4}
show_img = False # default: False
save_L = True # save LR image
save_E = True # save estimated image
# load approximated bicubic kernels
#kernels = hdf5storage.loadmat(os.path.join('kernels', 'kernels_bicubicx234.mat'))['kernels']
kernels = loadmat(os.path.join('kernels',
'kernels_bicubicx234.mat'))['kernels']
kernel = kernels[0, sf - 2].astype(np.float64)
kernel = util.single2tensor4(kernel[..., np.newaxis])
task_current = 'sr' # fixed, 'sr' for super-resolution
n_channels = 3 # fixed, 3 for color image
model_pool = 'model_zoo' # fixed
testsets = 'testsets' # fixed
results = 'results' # fixed
noise_level_img = 0 # fixed: 0, noise level for LR image
noise_level_model = noise_level_img # fixed, noise level of model, default 0
result_name = testset_name + '_' + model_name + '_bicubic'
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, fixed, for Low-quality images
H_path = L_path # H_path, 'None' | L_path, for High-quality images
E_path = os.path.join(results,
result_name) # E_path, fixed, 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_usrnet import USRNet as net # for pytorch version <= 1.7.1
# from models.network_usrnet_v1 import USRNet as net # for pytorch version >=1.8.1
if 'tiny' in model_name:
model = net(n_iter=6,
h_nc=32,
in_nc=4,
out_nc=3,
nc=[16, 32, 64, 64],
nb=2,
act_mode="R",
downsample_mode='strideconv',
upsample_mode="convtranspose")
else:
model = net(n_iter=8,
h_nc=64,
in_nc=4,
out_nc=3,
nc=[64, 128, 256, 512],
nb=2,
act_mode="R",
downsample_mode='strideconv',
upsample_mode="convtranspose")
model.load_state_dict(torch.load(model_path), strict=True)
model.eval()
for key, v in model.named_parameters():
v.requires_grad = False
number_parameters = sum(map(lambda x: x.numel(), model.parameters()))
logger.info('Params number: {}'.format(number_parameters))
model = model.to(device)
logger.info('Model path: {:s}'.format(model_path))
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
if need_degradation:
img_L = util.modcrop(img_L, sf)
img_L = util.imresize_np(img_L, 1 / sf)
# img_L = util.uint2single(util.single2uint(img_L))
# np.random.seed(seed=0) # for reproducibility
# img_L += np.random.normal(0, noise_level_img/255., img_L.shape)
w, h = img_L.shape[:2]
if save_L:
util.imsave(
util.single2uint(img_L),
os.path.join(E_path, img_name + '_LR_x' + str(sf) + '.png'))
img = cv2.resize(img_L, (sf * h, sf * w),
interpolation=cv2.INTER_NEAREST)
img = utils_deblur.wrap_boundary_liu(img, [
int(np.ceil(sf * w / 8 + 2) * 8),
int(np.ceil(sf * h / 8 + 2) * 8)
])
img_wrap = sr.downsample_np(img, sf, center=False)
img_wrap[:w, :h, :] = img_L
img_L = img_wrap
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
# ------------------------------------
sigma = torch.tensor(noise_level_model).float().view([1, 1, 1, 1])
[img_L, kernel,
sigma] = [el.to(device) for el in [img_L, kernel, sigma]]
img_E = model(img_L, kernel, sf, sigma)
img_E = util.tensor2uint(img_E)
img_E = img_E[:sf * w, :sf * h, :]
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
# ------------------------------------
if save_E:
util.imsave(
img_E,
os.path.join(
E_path,
img_name + '_x' + str(sf) + '_' + model_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))
def main():
utils_logger.logger_info('efficientsr_challenge',
log_path='efficientsr_challenge.log')
logger = logging.getLogger('efficientsr_challenge')
# print(torch.__version__) # pytorch version
# print(torch.version.cuda) # cuda version
# print(torch.backends.cudnn.version()) # cudnn version
# --------------------------------
# basic settings
# --------------------------------
model_names = ['msrresnet', 'imdn']
model_id = 1 # set the model name
model_name = model_names[model_id]
logger.info('{:>16s} : {:s}'.format('Model Name', model_name))
testsets = 'testsets' # set path of testsets
testset_L = 'DIV2K_valid_LR' # set current testing dataset; 'DIV2K_test_LR'
testset_L = 'set12'
save_results = True
print_modelsummary = True # set False when calculating `Max Memery` and `Runtime`
torch.cuda.set_device(0) # set GPU ID
logger.info('{:>16s} : {:<d}'.format('GPU ID',
torch.cuda.current_device()))
torch.cuda.empty_cache()
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
# --------------------------------
# define network and load model
# --------------------------------
if model_name == 'msrresnet':
from models.network_msrresnet import MSRResNet1 as net
model = net(in_nc=3, out_nc=3, nc=64, nb=16,
upscale=4) # define network
model_path = os.path.join('model_zoo',
'msrresnet_x4_psnr.pth') # set model path
elif model_name == 'imdn':
from models.network_imdn import IMDN as net
model = net(in_nc=3,
out_nc=3,
nc=64,
nb=8,
upscale=4,
act_mode='L',
upsample_mode='pixelshuffle') # define network
model_path = os.path.join('model_zoo', 'imdn_x4.pth') # set model path
model.load_state_dict(torch.load(model_path), strict=True)
model.eval()
for k, v in model.named_parameters():
v.requires_grad = False
model = model.to(device)
# --------------------------------
# print model summary
# --------------------------------
if print_modelsummary:
from utils.utils_modelsummary import get_model_activation, get_model_flops
input_dim = (3, 256, 256) # set the input dimension
activations, num_conv2d = get_model_activation(model, input_dim)
logger.info('{:>16s} : {:<.4f} [M]'.format('#Activations',
activations / 10**6))
logger.info('{:>16s} : {:<d}'.format('#Conv2d', num_conv2d))
flops = get_model_flops(model, input_dim, False)
logger.info('{:>16s} : {:<.4f} [G]'.format('FLOPs', flops / 10**9))
num_parameters = sum(map(lambda x: x.numel(), model.parameters()))
logger.info('{:>16s} : {:<.4f} [M]'.format('#Params',
num_parameters / 10**6))
# --------------------------------
# read image
# --------------------------------
L_path = os.path.join(testsets, testset_L)
E_path = os.path.join(testsets, testset_L + '_' + model_name)
util.mkdir(E_path)
# record runtime
test_results = OrderedDict()
test_results['runtime'] = []
logger.info('{:>16s} : {:s}'.format('Input Path', L_path))
logger.info('{:>16s} : {:s}'.format('Output Path', E_path))
idx = 0
start = torch.cuda.Event(enable_timing=True)
end = torch.cuda.Event(enable_timing=True)
for img in util.get_image_paths(L_path):
# --------------------------------
# (1) img_L
# --------------------------------
idx += 1
img_name, ext = os.path.splitext(os.path.basename(img))
logger.info('{:->4d}--> {:>10s}'.format(idx, img_name + ext))
img_L = util.imread_uint(img, n_channels=3)
img_L = util.uint2tensor4(img_L)
torch.cuda.empty_cache()
img_L = img_L.to(device)
start.record()
img_E = model(img_L)
# logger.info('{:>16s} : {:<.3f} [M]'.format('Max Memery', torch.cuda.max_memory_allocated(torch.cuda.current_device())/1024**2)) # Memery
end.record()
torch.cuda.synchronize()
test_results['runtime'].append(start.elapsed_time(end)) # milliseconds
# torch.cuda.synchronize()
# start = time.time()
# img_E = model(img_L)
# torch.cuda.synchronize()
# end = time.time()
# test_results['runtime'].append(end-start) # seconds
# --------------------------------
# (2) img_E
# --------------------------------
img_E = util.tensor2uint(img_E)
if save_results:
util.imsave(img_E, os.path.join(E_path, img_name + ext))
ave_runtime = sum(test_results['runtime']) / len(
test_results['runtime']) / 1000.0
logger.info('------> Average runtime of ({}) is : {:.6f} seconds'.format(
L_path, ave_runtime))
def main():
# ----------------------------------------
# Preparation
# ----------------------------------------
noise_level_img = 0 # default: 0, noise level for LR image
noise_level_model = noise_level_img # noise level for model
model_name = 'dpsr_x4_gan' # 'dpsr_x2' | 'dpsr_x3' | 'dpsr_x4' | 'dpsr_x4_gan'
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
nc = 96 # fixed, number of channels
nb = 16 # fixed, number of conv layers
model_pool = 'model_zoo' # fixed
testsets = 'testsets' # fixed
results = 'results' # fixed
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_dpsr import MSRResNet_prior as net
model = net(in_nc=n_channels + 1,
out_nc=n_channels,
nc=nc,
nb=nb,
upscale=sf,
act_mode='R',
upsample_mode='pixelshuffle')
model.load_state_dict(torch.load(model_path), 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:{}, model sigma:{}, image sigma:{}'.format(
model_name, noise_level_img, noise_level_model))
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)
noise_level_map = torch.full((1, 1, img_L.size(2), img_L.size(3)),
noise_level_model / 255.).type_as(img_L)
img_L = torch.cat((img_L, noise_level_map), dim=1)
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))
def main():
# ----------------------------------------
# Preparation
# ----------------------------------------
model_name = 'usrnet_tiny' # 'usrgan' | 'usrnet' | 'usrgan_tiny' | 'usrnet_tiny'
testset_name = 'srcvte' # test set, 'set5' | 'srbsd68' | 'srcvte'
test_sf = [
4
] # if 'gan' in model_name else [2, 3, 4] # scale factor, from {1,2,3,4}
load_kernels = False
show_img = False # default: False
save_L = False # save LR image
save_E = True # save estimated image
save_LEH = False # save zoomed LR, E and H images
# ----------------------------------------
# load testing kernels
# ----------------------------------------
# kernels = hdf5storage.loadmat(os.path.join('kernels', 'kernels.mat'))['kernels']
kernels = loadmat(os.path.join(
'kernels', 'kernels_12.mat'))['kernels'] if load_kernels else None
n_channels = 1 if 'gray' in model_name else 3 # 3 for color image, 1 for grayscale image
model_pool = '/home/dengzeshuai/pretrained_models/USRnet/' # fixed
testsets = '/home/datasets/sr/' # fixed
results = 'results' # fixed
noise_level_img = 0 # fixed: 0, noise level for LR image
noise_level_model = noise_level_img # fixed, noise level of model, default 0
result_name = testset_name + '_' + model_name + '_blur'
model_path = os.path.join(model_pool, model_name + '.pth')
# ----------------------------------------
# L_path = H_path, E_path, logger
# ----------------------------------------
L_path = os.path.join(
testsets,
testset_name) # L_path and H_path, fixed, for Low-quality images
if testset_name == 'srcvte':
L_path = os.path.join(testsets, testset_name, 'LR_val')
H_path = os.path.join(testsets, testset_name, 'HR_val')
video_names = os.listdir(H_path)
E_path = os.path.join(results,
result_name) # E_path, fixed, for Estimated images
util.mkdir(E_path)
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)
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
# ----------------------------------------
# load model
# ----------------------------------------
if 'tiny' in model_name:
model = net(n_iter=6,
h_nc=32,
in_nc=4,
out_nc=3,
nc=[16, 32, 64, 64],
nb=2,
act_mode="R",
downsample_mode='strideconv',
upsample_mode="convtranspose")
else:
model = net(n_iter=8,
h_nc=64,
in_nc=4,
out_nc=3,
nc=[64, 128, 256, 512],
nb=2,
act_mode="R",
downsample_mode='strideconv',
upsample_mode="convtranspose")
model.load_state_dict(torch.load(model_path), strict=True)
model.eval()
for key, v in model.named_parameters():
v.requires_grad = False
number_parameters = sum(map(lambda x: x.numel(), model.parameters()))
model = model.to(device)
logger.info('Model path: {:s}'.format(model_path))
logger.info('Params number: {}'.format(number_parameters))
logger.info('Model_name:{}, image sigma:{}'.format(model_name,
noise_level_img))
logger.info(L_path)
L_paths = util.get_image_paths(L_path)
need_H = True if H_path is not None else False
H_paths = util.get_image_paths(H_path) if need_H else None
# --------------------------------
# read images
# --------------------------------
test_results_ave = OrderedDict()
test_results_ave['psnr_sf_k'] = []
test_results_ave['ssim_sf_k'] = []
test_results_ave['psnr_y_sf_k'] = []
test_results_ave['ssim_y_sf_k'] = []
for sf in test_sf:
loop = kernels.shape[1] if load_kernels else 1
for k_index in range(loop):
test_results = OrderedDict()
test_results['psnr'] = []
test_results['ssim'] = []
test_results['psnr_y'] = []
test_results['ssim_y'] = []
if load_kernels:
kernel = kernels[0, k_index].astype(np.float64)
else:
## other kernels
# kernel = utils_deblur.blurkernel_synthesis(h=25) # motion kernel
kernel = utils_deblur.fspecial('gaussian', 25,
1.6) # Gaussian kernel
kernel = sr.shift_pixel(kernel, sf) # pixel shift; optional
kernel /= np.sum(kernel)
util.surf(kernel) if show_img else None
# idx = 0
for idx, img in enumerate(L_paths):
# --------------------------------
# (1) classical degradation, img_L
# --------------------------------
img_name, ext = os.path.splitext(os.path.basename(img))
if testset_name == 'srcvte':
video_name = os.path.basename(os.path.dirname(img))
img_L = util.imread_uint(img, n_channels=n_channels)
img_L = util.uint2single(img_L)
# generate degraded LR image
# img_L = ndimage.filters.convolve(img_H, kernel[..., np.newaxis], mode='wrap') # blur
# img_L = sr.downsample_np(img_L, sf, center=False) # downsample, standard s-fold downsampler
# img_L = util.uint2single(img_L) # uint2single
# np.random.seed(seed=0) # for reproducibility
# img_L += np.random.normal(0, noise_level_img, img_L.shape) # add AWGN
util.imshow(util.single2uint(img_L)) if show_img else None
x = util.single2tensor4(img_L)
k = util.single2tensor4(kernel[..., np.newaxis])
sigma = torch.tensor(noise_level_model).float().view(
[1, 1, 1, 1])
[x, k, sigma] = [el.to(device) for el in [x, k, sigma]]
# --------------------------------
# (2) inference
# --------------------------------
x = model(x, k, sf, sigma)
# --------------------------------
# (3) img_E
# --------------------------------
img_E = util.tensor2uint(x)
if save_E:
if testset_name == 'srcvte':
save_path = os.path.join(E_path, video_name)
util.mkdir(save_path)
# util.imsave(img_E, os.path.join(save_path, img_name+'_k'+str(k_index+1)+'.png'))
util.imsave(img_E,
os.path.join(save_path, img_name + '.png'))
else:
util.imsave(
img_E,
os.path.join(
E_path, img_name + '_x' + str(sf) + '_k' +
str(k_index + 1) + '_' + model_name + '.png'))
# --------------------------------
# (4) img_H
# --------------------------------
if need_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 = util.calculate_psnr(
img_E, img_H, border=sf) # change with your own border
ssim = util.calculate_ssim(img_E, img_H, border=sf)
test_results['psnr'].append(psnr)
test_results['ssim'].append(ssim)
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=sf)
ssim_y = util.calculate_ssim(img_E_y,
img_H_y,
border=sf)
test_results['psnr_y'].append(psnr_y)
test_results['ssim_y'].append(ssim_y)
logger.info(
'{:->4d} --> {:>4s}--> {:>10s} -- x{:>2d} --k{:>2d} PSNR: {:.2f}dB SSIM: {:.4f}'
.format(idx, video_name, img_name + ext, sf,
k_index, psnr_y, ssim_y))
else:
logger.info(
'{:->4d} --> {:>4s}--> {:>10s} -- x{:>2d} --k{:>2d} PSNR: {:.2f}dB SSIM: {:.4f}'
.format(idx, video_name, img_name + ext, sf,
k_index, psnr, ssim))
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))
logger.info(
'------> Average PSNR(RGB) - {} - x{}, kernel:{} sigma:{} --PSNR: {:.2f} dB; SSIM: {:.4f}'
.format(testset_name, sf, k_index + 1, noise_level_model,
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(Y) - {} - x{}, kernel:{} sigma:{} --PSNR: {:.2f} dB; SSIM: {:.4f}'
.format(testset_name, sf, k_index + 1,
noise_level_model, ave_psnr_y, ave_ssim_y))
test_results_ave['psnr_sf_k'].append(ave_psnr)
test_results_ave['ssim_sf_k'].append(ave_ssim)
if np.ndim(img_H) == 3:
test_results_ave['psnr_y_sf_k'].append(ave_psnr_y)
test_results_ave['ssim_y_sf_k'].append(ave_ssim_y)
logger.info(test_results_ave['psnr_sf_k'])
logger.info(test_results_ave['ssim_sf_k'])
if np.ndim(img_H) == 3:
logger.info(test_results_ave['psnr_y_sf_k'])
logger.info(test_results_ave['ssim_y_sf_k'])