def __init__(self, args, ckp): super(Model, self).__init__() print('Making model...') self.scale = args.scale self.idx_scale = 0 self.self_ensemble = args.self_ensemble self.chop = args.chop self.precision = args.precision self.cpu = args.cpu self.device = torch.device('cuda') self.n_GPUs = args.n_GPUs self.save_models = args.save_models self.kernel = fspecial('gaussian', 15, 2.6) self.k = single2tensor3(np.expand_dims(np.float32(self.kernel), axis=2)).unsqueeze(0) self.noise_level = np.random.randint(0, 25) / 255.0 self.sigma = torch.tensor(self.noise_level).float().view([1, 1, 1, 1]) self.k = (self.k).to(self.device) self.sigma = (self.sigma).to(self.device) # 1020后续添加选择模型的接口 from model import tiny_demo2 as module self.model = module.make_model().to(self.device) if args.precision == 'half': self.model.half() self.load(ckp.dir, pre_train=args.pre_train, resume=args.resume, cpu=args.cpu) print(self.model, file=ckp.log_file)
def get_kernel_sigma(): 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] k = utils_deblur.fspecial('gaussian', 25, kernel_width) k = sr.shift_pixel(k, sf) # shift the kernel k /= np.sum(k) kernel = util.single2tensor4(k[..., np.newaxis]) sigma = torch.tensor(noise_level_model).float().view([1, 1, 1, 1]) return kernel, sigma
def __getitem__(self, index): # 从文件中读出HR图片,返回HR、LR图片对 HR_path, LR_path = None, None HR_path = self.HR_paths[index] img_HR = util.read_img_(HR_path, self.n_colors) # 归一化 img_HR = util.unit2single(img_HR) img_HR = util.modcrop(img_HR, self.scale) kernel = fspecial('gaussian', 15, 2.6) H, W, _ = img_HR.shape img_LR = util.srmd_degradation(img_HR, kernel, self.scale) if self.opt.phase == 'train': patch_H, patch_L = util.paired_random_crop(img_HR, img_LR, self.patch_size, self.scale) # augmentation - flip, rotate img_HR, img_LR = util.augment([patch_H, patch_L], self.opt.use_flip, self.opt.use_rot) img_HR = util.img_single2tensor(img_HR) img_LR = util.img_single2tensor(img_LR) if random.random() < 0.1: noise_level = torch.zeros(1).float() else: noise_level = torch.FloatTensor([ np.random.uniform(self.sigma_min, self.sigma_max) ]) / 255.0 else: img_HR = util.img_single2tensor(img_HR) img_LR = util.img_single2tensor(img_LR) noise_level = torch.FloatTensor([self.sigma_test]) noise = torch.randn(img_LR.size()).mul_(noise_level).float() img_LR.add_(noise) kernel = util.single2tensor3(np.expand_dims(np.float32(kernel), axis=2)) noise_level = torch.FloatTensor([noise_level]).view([1, 1, 1]) if LR_path is None: LR_path = HR_path return { 'LR': img_LR, 'HR': img_HR, 'k': kernel, 'sigma': noise_level, 'sf': self.scale, 'LR_path': LR_path, 'HR_path': HR_path }
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 # ---------------------------------------- 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(): # ---------------------------------------- # 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(): model_name = 'msrresnet_x4_psnr' # 'msrresnet_x4_gan' | 'msrresnet_x4_psnr' testset_name = 'Set14' # test set, 'set5' | 'srbsd68' need_degradation = True # default: True x8 = False # default: False, x8 to boost performance, default: False sf = [int(s) for s in re.findall(r'\d+', model_name)][0] # scale factor show_img = False # default: False task_current = 'sr' # 'dn' for denoising | 'sr' for super-resolution n_channels = 3 # fixed model_pool = 'model_zoo' # fixed testsets = 'testsets' # fixed results = 'results' # fixed noise_level_img = 0 # fixed: 0, noise level for LR image result_name = testset_name + '_' + model_name border = sf if task_current == 'sr' else 0 # shave boader to calculate PSNR and SSIM model_path = os.path.join(model_pool, model_name + '.pth') # ---------------------------------------- # L_path, E_path, H_path # ---------------------------------------- L_path = os.path.join(testsets, testset_name) # L_path, for Low-quality images H_path = L_path # H_path, for High-quality images E_path = os.path.join(results, result_name) # E_path, for Estimated images util.mkdir(E_path) if H_path == L_path: need_degradation = True logger_name = result_name utils_logger.logger_info(logger_name, log_path=os.path.join(E_path, logger_name + '.log')) logger = logging.getLogger(logger_name) need_H = True if H_path is not None else False device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') # ---------------------------------------- # load model # ---------------------------------------- from models.network_msrresnet import MSRResNet1 as net model = net(in_nc=n_channels, out_nc=n_channels, nc=64, nb=16, upscale=4) 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'] = [] 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(H_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_H = util.uint2single(img_H) # degradation process, bicubic downsampling if need_degradation: img_H = util.modcrop(img_H, sf) # img_L = util.imresize_np(img_L, 1/sf) kernel = fspecial('gaussian', 15, 2.6) img_L = utils_sisr.srmd_degradation(img_H, kernel, 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) # util.imshow(util.single2uint(img_L), title='LR image with noise level {}'.format(noise_level_img)) if show_img else None img_L = util.single2tensor4(img_L) img_L = img_L.to(device) # ------------------------------------ # (2) img_E # ------------------------------------ if not x8: img_E = model(img_L) else: img_E = utils_model.test_mode(model, img_L, mode=3, sf=sf) img_E = util.tensor2uint(img_E) if need_H: # -------------------------------- # (3) img_H # -------------------------------- img_H = util.imread_uint(H_paths[idx], n_channels=n_channels) img_H = img_H.squeeze() img_H = util.modcrop(img_H, sf) # -------------------------------- # PSNR and SSIM # -------------------------------- psnr = util.calculate_psnr(img_E, img_H, border=border) ssim = util.calculate_ssim(img_E, img_H, border=border) test_results['psnr'].append(psnr) test_results['ssim'].append(ssim) logger.info('{:s} - PSNR: {:.2f} dB; SSIM: {:.4f}.'.format( img_name + ext, psnr, ssim)) util.imshow(np.concatenate([img_E, img_H], axis=1), title='Recovered / Ground-truth') if show_img else None if np.ndim(img_H) == 3: # RGB image img_E_y = util.rgb2ycbcr(img_E, only_y=True) img_H_y = util.rgb2ycbcr(img_H, only_y=True) psnr_y = util.calculate_psnr(img_E_y, img_H_y, border=border) ssim_y = util.calculate_ssim(img_E_y, img_H_y, border=border) test_results['psnr_y'].append(psnr_y) test_results['ssim_y'].append(ssim_y) # ------------------------------------ # save results # ------------------------------------ util.imsave(img_E, os.path.join(E_path, img_name + '.png')) if need_H: ave_psnr = sum(test_results['psnr']) / len(test_results['psnr']) ave_ssim = sum(test_results['ssim']) / len(test_results['ssim']) logger.info( 'Average PSNR/SSIM(RGB) - {} - x{} --PSNR: {:.3f} 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(): # -------------------------------- # let's start! # -------------------------------- utils_logger.logger_info('test_dpsr_real', log_path='test_dpsr_real.log') logger = logging.getLogger('test_dpsr_real') global arg arg = parser.parse_args() # basic setting # ================================================ sf = arg.sf show_img = False noise_level_img = 8. / 255. #testsets = '/home/share2/wutong/DPSR/testsets/test/' #im = '0000115_01031_d_0000082.jpg' # chip.png colour.png # if 'chip' in im: # noise_level_img = 8./255. # elif 'colour' in im: #noise_level_img = 0.5/255. use_srganplus = False if use_srganplus and sf == 4: model_prefix = 'DPSRGAN' save_suffix = 'dpsrgan' else: model_prefix = 'DPSR' save_suffix = 'dpsr' model_path = os.path.join('DPSR_models', model_prefix + 'x%01d.pth' % (sf)) iter_num = 15 # number of iterations n_channels = 3 # only color images, fixed # ================================================ device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') # -------------------------------- # (1) load trained model # -------------------------------- model = SRResNet(in_nc=4, out_nc=3, nc=96, nb=16, upscale=sf, act_mode='R', upsample_mode='pixelshuffle') 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}. Testing...'.format(model_path)) # -------------------------------- # (2) L_folder, E_folder # -------------------------------- # --1--> L_folder, folder of Low-quality images L_folder = os.path.join(arg.load) # L: Low quality # --2--> E_folder, folder of Estimated images E_folder = os.path.join(arg.save) util.mkdir(E_folder) logger.info(L_folder) # for im in os.listdir(os.path.join(L_folder)): # if (im.endswith('.jpg') or im.endswith('.bmp') or im.endswith('.png')) and 'kernel' not in im: # -------------------------------- # (3) load low-resolution image # -------------------------------- img_list = os.listdir(L_folder) for im in img_list: img_path, ext = os.path.splitext(im) img_name = img_path.split('/')[-1] img = util.imread_uint(os.path.join(L_folder, im), n_channels=n_channels) h, w = img.shape[:2] util.imshow(img, title='Low-resolution image') if show_img else None img = util.unit2single(img) # -------------------------------- # (4) load blur kernel # -------------------------------- # if os.path.exists(os.path.join(L_folder, img_name+'_kernel.mat')): # k = loadmat(os.path.join(L_folder, img_name+'.mat'))['kernel'] # k = k.astype(np.float64) # k /= k.sum() # elif os.path.exists(os.path.join(L_folder, img_name+'_kernel.png')): # k = cv2.imread(os.path.join(L_folder, img_name+'_kernel.png'), 0) # k = np.float64(k) # float64 ! # k /= k.sum() #else: k = utils_deblur.fspecial('gaussian', 5, 0.25) iter_num = 5 # -------------------------------- # (5) handle boundary # -------------------------------- img = utils_deblur.wrap_boundary_liu( img, utils_deblur.opt_fft_size( [img.shape[0] + k.shape[0] + 1, img.shape[1] + k.shape[1] + 1])) # -------------------------------- # (6) get upperleft, denominator # -------------------------------- upperleft, denominator = utils_deblur.get_uperleft_denominator(img, k) # -------------------------------- # (7) get rhos and sigmas # -------------------------------- rhos, sigmas = utils_deblur.get_rho_sigma(sigma=max( 0.255 / 255.0, noise_level_img), iter_num=iter_num) # -------------------------------- # (8) main iteration # -------------------------------- z = img rhos = np.float32(rhos) sigmas = np.float32(sigmas) for i in range(iter_num): logger.info('Iter: {:->4d}--> {}'.format(i + 1, im)) # -------------------------------- # step 1, Eq. (9) // FFT # -------------------------------- rho = rhos[i] if i != 0: z = util.imresize_np(z, 1 / sf, True) z = np.real( np.fft.ifft2((upperleft + rho * np.fft.fft2(z, axes=(0, 1))) / (denominator + rho), axes=(0, 1))) # -------------------------------- # step 2, Eq. (12) // super-resolver # -------------------------------- sigma = torch.from_numpy(np.array(sigmas[i])) img_L = util.single2tensor4(z) noise_level_map = torch.ones((1, 1, img_L.size(2), img_L.size(3)), dtype=torch.float).mul_(sigma) img_L = torch.cat((img_L, noise_level_map), dim=1) img_L = img_L.to(device) # with torch.no_grad(): z = model(img_L) z = util.tensor2single(z) # -------------------------------- # (9) img_E # -------------------------------- img_E = util.single2uint( z[:h * sf, :w * sf]) # np.uint8((z[:h*sf, :w*sf] * 255.0).round()) logger.info('saving: sf = {}, {}.'.format( sf, img_name + '_x{}'.format(sf) + ext)) util.imsave(img_E, os.path.join(E_folder, img_name + ext)) util.imshow(img_E, title='Recovered image') if show_img else None
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 # ---------------------------------------- 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'])