def show_pca(x):
"""
x: PCA projection matrix, e.g., 15x225
"""
for i in range(x.shape[0]):
xc = np.reshape(x[i, :], (int(np.sqrt(x.shape[1])), -1), order="F")
util.surf(xc)
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():
# ----------------------------------------
# Preparation
# ----------------------------------------
model_name = 'usrnet' # 'usrgan' | 'usrnet' | 'usrgan_tiny' | 'usrnet_tiny'
testset_name = 'set_real' # test set, 'set_real'
test_image = 'chip.png' # 'chip.png', 'comic.png'
#test_image = 'comic.png'
sf = 4 # scale factor, only from {1, 2, 3, 4}
show_img = False # default: False
save_E = True # save estimated image
save_LE = True # save zoomed LR, Estimated images
# ----------------------------------------
# set noise level and kernel
# ----------------------------------------
if 'chip' in test_image:
noise_level_img = 15 # noise level for LR image, 15 for chip
kernel_width_default_x1234 = [0.6, 0.9, 1.7, 2.2] # Gaussian kernel widths for x1, x2, x3, x4
else:
noise_level_img = 2 # noise level for LR image, 0.5~3 for clean images
kernel_width_default_x1234 = [0.4, 0.7, 1.5, 2.0] # default Gaussian kernel widths of clean/sharp images 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 = 2.2
k = utils_deblur.fspecial('gaussian', 25, kernel_width)
k = sr.shift_pixel(k, sf) # shift the kernel
k /= np.sum(k)
util.surf(k) if show_img else None
# scio.savemat('kernel_realapplication.mat', {'kernel':k})
# load approximated bicubic kernels
#kernels = hdf5storage.loadmat(os.path.join('kernels', 'kernel_bicubicx234.mat'))['kernels']
# kernels = loadmat(os.path.join('kernels', 'kernel_bicubicx234.mat'))['kernels']
# kernel = kernels[0, sf-2].astype(np.float64)
kernel = util.single2tensor4(k[..., np.newaxis])
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
result_name = testset_name + '_' + model_name
model_path = os.path.join(model_pool, model_name+'.pth')
# ----------------------------------------
# L_path, E_path
# ----------------------------------------
L_path = os.path.join(testsets, testset_name) # L_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()))
logger.info('Params number: {}'.format(number_parameters))
model = model.to(device)
logger.info('Model path: {:s}'.format(model_path))
logger.info('model_name:{}, image sigma:{}'.format(model_name, noise_level_img))
logger.info(L_path)
img = os.path.join(L_path, test_image)
# ------------------------------------
# (1) img_L
# ------------------------------------
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)
util.imshow(img_L) if show_img else None
w, h = img_L.shape[:2]
logger.info('{:>10s}--> ({:>4d}x{:<4d})'.format(img_name+ext, w, h))
# boundary handling
boarder = 8 # default setting for kernel size 25x25
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/boarder+2)*boarder), int(np.ceil(sf*h/boarder+2)*boarder)])
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)[:sf*w, :sf*h, ...]
if save_E:
util.imsave(img_E, os.path.join(E_path, img_name+'_x'+str(sf)+'_'+model_name+'.png'))
# --------------------------------
# (3) save img_LE
# --------------------------------
if save_LE:
k_v = k/np.max(k)*1.2
k_v = util.single2uint(np.tile(k_v[..., np.newaxis], [1, 1, 3]))
k_factor = 3
k_v = cv2.resize(k_v, (k_factor*k_v.shape[1], k_factor*k_v.shape[0]), interpolation=cv2.INTER_NEAREST)
img_L = util.tensor2uint(img_L)[:w, :h, ...]
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
util.imshow(np.concatenate([img_I, img_E], axis=1), title='LR / Recovered') if show_img else None
util.imsave(np.concatenate([img_I, img_E], axis=1), os.path.join(E_path, img_name+'_x'+str(sf)+'_'+model_name+'_LE.png'))
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))
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'])
