def main(): # ---------------------------------------- # load kernels # ---------------------------------------- motion_id = 7 PSF_grid = np.load('./data/Motion_PSF_{}.npz'.format(motion_id))['PSF'] PSF_grid = PSF_grid.astype(np.float32) gx, gy = PSF_grid.shape[:2] k_tensor = [] for yy in range(gy): for xx in range(gx): PSF_grid[xx, yy] = PSF_grid[xx, yy] / np.sum(PSF_grid[xx, yy], axis=(0, 1)) k_tensor.append(util.single2tensor4(PSF_grid[xx, yy])) k_tensor = torch.cat(k_tensor, dim=0) inv_weight = util_deblur.get_inv_spatial_weight(k_tensor) # ---------------------------------------- # load model # ---------------------------------------- stage = 8 model_code = 'iter4700' global_iter = 4700 device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') model = net(n_iter=stage, 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") pre_files = '/home/xiu/databag/deblur/models/motion/uabcnet_{}_{}.pth'.format( motion_id, model_code) model.load_state_dict(torch.load(pre_files), strict=True) model.train() for _, v in model.named_parameters(): v.requires_grad = True model = model.to(device) # ---------------------------------------- # load training data # ---------------------------------------- imgs = glob.glob('/home/xiu/databag/deblur/images/*/**.png', recursive=True) imgs.sort() # ---------------------------------------- # positional lambda\mu for HQS # ---------------------------------------- ab_buffer = np.ones((gx, gy, 2 * stage, 3), dtype=np.float32) * 0.1 #ab_buffer[:,:,0,:] = 0.01 #ab_buffer = np.loadtxt('/home/xiu/databag/deblur/models/motion/ab_{}.txt'.format(model_code)).astype(np.float32).reshape(gx,gy,stage*2,3) ab = torch.tensor(ab_buffer, device=device, requires_grad=True) # ---------------------------------------- # build optimizer # ---------------------------------------- params = [] params += [{"params": [ab], "lr": 0.0005}] for key, value in model.named_parameters(): params += [{"params": [value], "lr": 0.0001}] optimizer = torch.optim.Adam(params, lr=0.0001, betas=(0.9, 0.999)) scheduler = torch.optim.lr_scheduler.StepLR(optimizer, step_size=300, gamma=0.9) #64x3 = 192 patch_size = [128, 128] expand = PSF_grid.shape[2] // 2 patch_num = [2, 2] batch_num = 1 vis = True #weight for each patch based on the spectral radius loss_weight = torch.ones((3, gx, gy), device=device) loss_weight.requires_grad = False running = True while running: #alpha.beta img_idx = np.random.randint(len(imgs)) img = imgs[img_idx] img_H = cv2.imread(img) w, h = img_H.shape[:2] loss = 0 save_image = [] for _ in range(batch_num): #focus on the edges mode = np.random.randint(8) px_start = np.random.randint(0, gx - patch_num[0] + 1) py_start = np.random.randint(0, gy - patch_num[1] + 1) if mode == 0: px_start = 0 if mode == 1: px_start = gx - patch_num[0] if mode == 2: py_start = 0 if mode == 3: py_start = gy - patch_num[1] x_start = np.random.randint( 0, w - patch_size[0] * patch_num[0] - expand * 2 + 1) y_start = np.random.randint( 0, h - patch_size[1] * patch_num[1] - expand * 2 + 1) PSF_patch = PSF_grid[px_start:px_start + patch_num[0], py_start:py_start + patch_num[1]] patch_H = img_H[x_start:x_start+patch_size[0]*patch_num[0]+expand*2,\ y_start:y_start+patch_size[1]*patch_num[1]+expand*2] patch_L = util_deblur.blockConv2d(patch_H, PSF_patch, expand) block_expand = max(patch_size[0] // 8, expand) patch_L_wrap = util_deblur.wrap_boundary_liu( patch_L, (patch_size[0] * patch_num[0] + block_expand * 2, patch_size[1] * patch_num[1] + block_expand * 2)) patch_L_wrap = np.hstack( (patch_L_wrap[:, -block_expand:, :], patch_L_wrap[:, :patch_size[1] * patch_num[1] + block_expand, :])) patch_L_wrap = np.vstack( (patch_L_wrap[-block_expand:, :, :], patch_L_wrap[:patch_size[0] * patch_num[0] + block_expand, :, :])) x = util.uint2single(patch_L_wrap) x = util.single2tensor4(x) x_gt = util.uint2single(patch_H[expand:-expand, expand:-expand]) x_gt = util.single2tensor4(x_gt) inv_weight_patch = torch.ones_like(x_gt) k_local = [] for h_ in range(patch_num[1]): for w_ in range(patch_num[0]): inv_weight_patch[0, 0, w_ * patch_size[0]:(w_ + 1) * patch_size[0], h_ * patch_size[1]:(h_ + 1) * patch_size[1]] = inv_weight[w_ + h_ * patch_num[0], 0] inv_weight_patch[0, 1, w_ * patch_size[0]:(w_ + 1) * patch_size[0], h_ * patch_size[1]:(h_ + 1) * patch_size[1]] = inv_weight[w_ + h_ * patch_num[0], 1] inv_weight_patch[0, 2, w_ * patch_size[0]:(w_ + 1) * patch_size[0], h_ * patch_size[1]:(h_ + 1) * patch_size[1]] = inv_weight[w_ + h_ * patch_num[0], 2] k_local.append(k_tensor[w_ + h_ * patch_num[0]:w_ + h_ * patch_num[0] + 1]) k = torch.cat(k_local, dim=0) [x, x_gt, k, inv_weight_patch ] = [el.to(device) for el in [x, x_gt, k, inv_weight_patch]] ab_patch = F.softplus(ab[px_start:px_start + patch_num[0], py_start:py_start + patch_num[1]]) cd = [] for h_ in range(patch_num[1]): for w_ in range(patch_num[0]): cd.append(ab_patch[w_:w_ + 1, h_]) cd = torch.cat(cd, dim=0) x_E = model.forward_patchwise(x, k, cd, patch_num, patch_size) predict = x_E[...,block_expand:block_expand+patch_size[0]*patch_num[0],\ block_expand:block_expand+patch_size[1]*patch_num[1]] loss += F.l1_loss(predict.div(inv_weight_patch), x_gt.div(inv_weight_patch)) patch_L = patch_L_wrap.astype(np.uint8) patch_E = util.tensor2uint(x_E)[block_expand:-block_expand, block_expand:-block_expand] show = np.hstack((patch_H[expand:-expand, expand:-expand], patch_L[block_expand:-block_expand, block_expand:-block_expand], patch_E)) save_image.append(show) optimizer.zero_grad() loss.backward() optimizer.step() scheduler.step() print('iter:{},loss {}'.format(global_iter + 1, loss.item())) save_image = np.vstack(save_image) if vis: cv2.imshow('HL', save_image) key = cv2.waitKey(1) global_iter += 1 if global_iter % 100 == 0: ab_numpy = ab.detach().cpu().numpy().flatten() torch.save( model.state_dict(), '/home/xiu/databag/deblur/models/bench/uabcnet_iter{}.pth'. format(global_iter)) np.savetxt( '/home/xiu/databag/deblur/models/bench/ab_iter{}.txt'.format( global_iter), ab_numpy) cv2.imwrite( '/home/xiu/databag/deblur/models/bench/show_iter{}.png'.format( global_iter), save_image) if vis and key == ord('q'): running = False break
def main(): #0. global config #scale factor sf = 4 stage = 8 patch_size = [32,32] patch_num = [2,2] #1. local PSF #shape: gx,gy,kw,kw,3 all_PSFs = load_kernels('./data') #2. local model device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') model = net(n_iter=8, h_nc=64, in_nc=4, out_nc=3, nc=[64, 128, 256, 512], nb=2,sf=sf, act_mode="R", downsample_mode='strideconv', upsample_mode="convtranspose") #loaded_state_dict= torch.load('./data/uabcnet_final.pth') loaded_state_dict= torch.load('./data/uabcnet_finetune.pth') model.load_state_dict(loaded_state_dict,strict=True) model.eval() for _, v in model.named_parameters(): v.requires_grad = False model = model.to(device) #positional lambda, mu for HQS, set as free trainable parameters here. ab_buffer = np.loadtxt('./data/ab.txt').reshape((patch_num[0],patch_num[1],2*stage,3)).astype(np.float32) #ab[2x2,2*stage,3] #ab_buffer = np.ones((patch_num[0],patch_num[1],2*stage,3),dtype=np.float32)*0.1 ab = torch.tensor(ab_buffer,device=device,requires_grad=False) #ab = F.softplus(ab) #3.load training data imgs_H = glob.glob('/home/xiu/databag/deblur/images/DIV2K_train/*.png',recursive=True) imgs_H.sort() global_iter = 0 N_maxiter = 1000 PSF_grid = using_AC254_lens(all_PSFs,patch_num) all_PSNR = [] for i in range(N_maxiter): #draw random image. img_idx = np.random.randint(len(imgs_H)) img_H = cv2.imread(imgs_H[img_idx]) patch_L,patch_H,patch_psf = draw_training_pair(img_H,PSF_grid,sf,patch_num,patch_size) x = util.uint2single(patch_L) x = util.single2tensor4(x) x_gt = util.uint2single(patch_H) x_gt = util.single2tensor4(x_gt) k_local = [] for h_ in range(patch_num[1]): for w_ in range(patch_num[0]): k_local.append(util.single2tensor4(patch_psf[w_,h_])) k = torch.cat(k_local,dim=0) [x,x_gt,k] = [el.to(device) for el in [x,x_gt,k]] ab_patch = F.softplus(ab) ab_patch_v = [] for h_ in range(patch_num[1]): for w_ in range(patch_num[0]): ab_patch_v.append(ab_patch[w_:w_+1,h_]) ab_patch_v = torch.cat(ab_patch_v,dim=0) x_E = model.forward_patchwise_SR(x,k,ab_patch_v,patch_num,[patch_size[0],patch_size[1]],sf) patch_L = cv2.resize(patch_L,dsize=None,fx=sf,fy=sf,interpolation=cv2.INTER_NEAREST) patch_E = util.tensor2uint((x_E)) psnr = cv2.PSNR(patch_E,patch_H) all_PSNR.append(psnr) show = np.hstack((patch_H,patch_L,patch_E))
def main(): args = parse_args() noise_level_img = args.ID_noise # noise level for noisy image noise_level_model = noise_level_img # noise level for model model_name = args.ID_model # 'ffdnet_gray' | 'ffdnet_color' | 'ffdnet_color_clip' | 'ffdnet_gray_clip' testset_name = 'CBSD68' # test set, 'bsd68' | 'cbsd68' | 'set12' need_degradation = True # default: True 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 = '/workspace/xuma/PAIR/KAIR/model_zoo' # fixed model_path = os.path.join(model_pool, model_name+'.pth') device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') 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) img_name, ext = os.path.splitext(args.test_image) img_L = util.imread_uint(args.test_image, 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)) 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) img_E = model(img_L, sigma) img_E = util.tensor2uint(img_E) save_path = os.path.join(args.ID_savepath, os.path.split(img_name)[1]+"_denoising"+str(args.ID_noise)+ext) util.imsave(img_E, save_path) print(f"Denoised image is saved to {save_path}")
def main(): # ---------------------------------------- # load kernels # ---------------------------------------- #PSF_grid = np.load('./data/AC254-075-A-ML-Zemax(ZMX).npz')['PSF'] PSF_grid = np.load('./data/Schuler_PSF_facade.npz')['PSF'] PSF_grid = PSF_grid.astype(np.float32) gx, gy = PSF_grid.shape[:2] for xx in range(gx): for yy in range(gy): PSF_grid[xx, yy] = PSF_grid[xx, yy] / np.sum(PSF_grid[xx, yy], axis=(0, 1)) # ---------------------------------------- # load model # ---------------------------------------- stage = 8 device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') model = net(n_iter=stage, 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_code = 'iter1500' loaded_state = torch.load( '/home/xiu/databag/deblur/models/facade/uabcnet_{}.pth'.format( model_code)) #strip_state = strip_prefix_if_present(loaded_state,prefix="p.") model.load_state_dict(loaded_state, strict=True) model.eval() for _, v in model.named_parameters(): v.requires_grad = False model = model.to(device) for img_id in range(1, 237): #for img_id in range(1,12): #img_L = cv2.imread('/home/xiu/workspace/UABC/ICCV2021/video1-3/res/2_{:03d}.bmp'.format(img_id)) #img_L = cv2.imread('/home/xiu/workspace/UABC/ICCV2021/video/{:08d}.bmp'.format(img_id)) #img_L = cv2.imread('/home/xiu/databag/deblur/ICCV2021/suo_image/{}/AC254-075-A-ML-Zemax(ZMX).bmp'.format(img_id)) #img_L = cv2.imread('/home/xiu/workspace/UABC/ICCV2021/ResolutionChart/Reso.bmp') img_L = cv2.imread( '/home/xiu/databag/deblur/ICCV2021/MPI_data/facade/blurry.jpg') img_L = img_L.astype(np.float32) #img_L = np.pad(img_L,((1,1),(61,62),(0,0)),mode='edge') full_img = img_L.copy() weight = full_img.copy() W, H = img_L.shape[:2] num_patch = [gx, gx] #positional alpha-beta parameters for HQS #ab_numpy = np.ones((num_patch*num_patch,17,1,1),dtype=np.float32)*0.1 #ab_numpy[:,0,:,:] = 0.01 ab_numpy = np.loadtxt( '/home/xiu/databag/deblur/models/facade/ab_{}.txt'.format( model_code)).astype(np.float32).reshape(gx, gy, stage * 2, 3) #ab_numpy = ab_numpy[:,1:-1,:,:] #ab_numpy = ab_numpy[...,None,None] ab = torch.tensor(ab_numpy, device=device, requires_grad=False) #save img_L t0 = time.time() px_start = 0 for py_start in range(0, gy - gx + 1, 1): PSF_patch = PSF_grid[px_start:px_start + num_patch[0], py_start:py_start + num_patch[1]] #block_expand = 1 patch_L = img_L[px_start * W // gx:(px_start + num_patch[0]) * W // gx, py_start * H // gy:(py_start + num_patch[1]) * H // gy, :] p_W, p_H = patch_L.shape[:2] expand = max(PSF_grid.shape[2] // 2, p_W // 16) block_expand = expand patch_L_wrap = util_deblur.wrap_boundary_liu( patch_L, (p_W + block_expand * 2, p_H + block_expand * 2)) #centralize patch_L_wrap = np.hstack((patch_L_wrap[:, -block_expand:, :], patch_L_wrap[:, :p_H + block_expand, :])) patch_L_wrap = np.vstack((patch_L_wrap[-block_expand:, :, :], patch_L_wrap[:p_W + block_expand, :, :])) x = util.uint2single(patch_L_wrap) x = util.single2tensor4(x) k_all = [] for h_ in range(num_patch[1]): for w_ in range(num_patch[0]): k_all.append(util.single2tensor4(PSF_patch[w_, h_])) k = torch.cat(k_all, dim=0) [x, k] = [el.to(device) for el in [x, k]] ab_patch = F.softplus(ab[px_start:px_start + num_patch[0], py_start:py_start + num_patch[1]]) cd = [] for h_ in range(num_patch[1]): for w_ in range(num_patch[0]): cd.append(ab_patch[w_:w_ + 1, h_]) cd = torch.cat(cd, dim=0) x_E = model.forward_patchwise(x, k, cd, num_patch, [W // gx, H // gy]) x_E = x_E[..., block_expand:block_expand + p_W, block_expand:block_expand + p_H] patch_L = patch_L_wrap.astype(np.uint8) patch_E = util.tensor2uint(x_E) if py_start == 0 or py_start == gy - gx: full_img[px_start * W // gx:(px_start + num_patch[0]) * W // gx, py_start * H // gy:(py_start + num_patch[1]) * H // gy, :] = patch_E else: full_img[px_start * W // gx:(px_start + num_patch[0]) * W // gx, py_start * H // gy:(py_start + num_patch[1]) * H // gy, :] = patch_E t1 = time.time() print(py_start) print(t1 - t0) # print(i) xk = patch_E # #zk = zk.astype(np.uint8) xk = full_img.astype(np.uint8) #cv2.imwrite('/home/xiu/workspace/UABC/ICCV2021/new_image/image/ours-{}.png'.format(img_id),xk) #cv2.imwrite('/home/xiu/workspace/UABC/ICCV2021/video_deblur/{:08d}.png'.format(img_id),xk) #cv2.imwrite('/home/xiu/workspace/UABC/ICCV2021/cap_result/1_{:03d}.png'.format(img_id),xk) cv2.imshow('xx', xk) cv2.imshow('img_L', img_L.astype(np.uint8)) key = cv2.waitKey(-1) if key == ord('q'): break
def main(): # ---------------------------------------- # Preparation # ---------------------------------------- model_name = '1000_G' # 'usrgan' | 'usrnet' | 'usrgan_tiny' | 'usrnet_tiny' testset_name = 'set_real' # 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="BR", 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="BR", 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 = 'usrgan' # 'usrgan' | 'usrnet' | 'usrgan_tiny' | 'usrnet_tiny' testset_name = 'set_real' # test set, 'set_real' test_image = 'test.png' # 'chip.png', 'comic.png' #test_image = 'comic.png' sf = 1 # scale factor, only from {1, 2, 3, 4} show_img = True # 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 # ---------------------------------------- model_name = 'usrgan' # 'usrgan' | 'usrnet' | 'usrgan_tiny' | 'usrnet_tiny' testset_name = 'set5' # test set, 'set5' | 'srbsd68' need_degradation = False # 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 = '/home/dengzeshuai/pretrained_models/USRnet/' # 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 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(): # ---------------------------------------- # Preparation # ---------------------------------------- model_name = '300000_G' # 'msrresnet_x4_gan' | 'msrresnet_x4_psnr' testset_name = 'testing_lr_images' # test set, 'set5' | 'srbsd68' need_degradation = False # default: True x8 = False # default: False, x8 to boost performance, default: False sf = 3 #[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 = './superresolution/msrresnet_psnr/models/' # fixed testsets = 'testsets' # fixed results = 'results' # fixed noise_level_img = 0 # fixed: 0, noise level for LR image result_name = testset_name + '_' + model_name + '_msrresnet' 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 = None # 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 os.environ["CUDA_VISIBLE_DEVICES"] = '8' 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=3) 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:{}, 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) util.imshow(util.single2uint(img_L), title='LR image with noise level {}'.format( noise_level_img)) if show_img else None img_L = util.single2tensor4(img_L) img_L = img_L.to(device) # ------------------------------------ # (2) img_E # ------------------------------------ if not x8: img_E = model(img_L) else: img_E = utils_model.test_mode(model, img_L, mode=3, sf=sf) img_E = util.tensor2uint(img_E) if need_H: # -------------------------------- # (3) img_H # -------------------------------- img_H = util.imread_uint(H_paths[idx], n_channels=n_channels) img_H = img_H.squeeze() img_H = util.modcrop(img_H, sf) # -------------------------------- # PSNR and SSIM # -------------------------------- psnr = util.calculate_psnr(img_E, img_H, border=border) ssim = util.calculate_ssim(img_E, img_H, border=border) test_results['psnr'].append(psnr) test_results['ssim'].append(ssim) logger.info('{:s} - PSNR: {:.2f} dB; SSIM: {:.4f}.'.format( img_name + ext, psnr, ssim)) util.imshow(np.concatenate([img_E, img_H], axis=1), title='Recovered / Ground-truth') if show_img else None if np.ndim(img_H) == 3: # RGB image img_E_y = util.rgb2ycbcr(img_E, only_y=True) img_H_y = util.rgb2ycbcr(img_H, only_y=True) psnr_y = util.calculate_psnr(img_E_y, img_H_y, border=border) ssim_y = util.calculate_ssim(img_E_y, img_H_y, border=border) test_results['psnr_y'].append(psnr_y) test_results['ssim_y'].append(ssim_y) # ------------------------------------ # save results # ------------------------------------ util.imsave(img_E, os.path.join(E_path, img_name + '.png')) if need_H: ave_psnr = sum(test_results['psnr']) / len(test_results['psnr']) ave_ssim = sum(test_results['ssim']) / len(test_results['ssim']) logger.info( 'Average PSNR/SSIM(RGB) - {} - x{} --PSNR: {:.2f} dB; SSIM: {:.4f}' .format(result_name, sf, ave_psnr, ave_ssim)) if np.ndim(img_H) == 3: ave_psnr_y = sum(test_results['psnr_y']) / len( test_results['psnr_y']) ave_ssim_y = sum(test_results['ssim_y']) / len( test_results['ssim_y']) logger.info( 'Average PSNR/SSIM( Y ) - {} - x{} - PSNR: {:.2f} dB; SSIM: {:.4f}' .format(result_name, sf, ave_psnr_y, ave_ssim_y))
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'])
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].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=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(): # ---------------------------------------- # load kernels # ---------------------------------------- PSF_grid = np.load('./data/AC254-075-A-ML-Zemax(ZMX).npz')['PSF'] PSF_grid = PSF_grid.astype(np.float32) gx, gy = PSF_grid.shape[:2] for xx in range(gx): for yy in range(gy): PSF_grid[xx, yy] = PSF_grid[xx, yy] / np.sum(PSF_grid[xx, yy], axis=(0, 1)) # ---------------------------------------- # load model # ---------------------------------------- stage = 8 device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') model = net(n_iter=stage, 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_code = 'iter17000' loaded_state = torch.load( '/home/xiu/databag/deblur/models/ZEMAX/uabcnet_{}.pth'.format( model_code)) model.load_state_dict(loaded_state, strict=True) model.eval() for _, v in model.named_parameters(): v.requires_grad = False model = model.to(device) img_names = glob.glob( '/home/xiu/databag/deblur/ICCV2021/suo_image/*/AC254-075-A-ML-Zemax(ZMX).bmp' ) img_names.sort() for img_id, img_name in enumerate(img_names): img_L = cv2.imread(img_name) img_L = img_L.astype(np.float32) W, H = img_L.shape[:2] num_patch = [6, 8] #positional alpha-beta parameters for HQS ab_numpy = np.loadtxt( '/home/xiu/databag/deblur/models/ZEMAX/ab_{}.txt'.format( model_code)).astype(np.float32).reshape(gx, gy, stage * 2, 3) ab = torch.tensor(ab_numpy, device=device, requires_grad=False) #save img_L t0 = time.time() px_start = 0 py_start = 0 PSF_patch = PSF_grid[px_start:px_start + num_patch[0], py_start:py_start + num_patch[1]] #block_expand = 1 patch_L = img_L[px_start * W // gx:(px_start + num_patch[0]) * W // gx, py_start * H // gy:(py_start + num_patch[1]) * H // gy, :] p_W, p_H = patch_L.shape[:2] expand = max(PSF_grid.shape[2] // 2, p_W // 16) block_expand = expand patch_L_wrap = util_deblur.wrap_boundary_liu( patch_L, (p_W + block_expand * 2, p_H + block_expand * 2)) #centralize patch_L_wrap = np.hstack((patch_L_wrap[:, -block_expand:, :], patch_L_wrap[:, :p_H + block_expand, :])) patch_L_wrap = np.vstack((patch_L_wrap[-block_expand:, :, :], patch_L_wrap[:p_W + block_expand, :, :])) x = util.uint2single(patch_L_wrap) x = util.single2tensor4(x) k_all = [] for h_ in range(num_patch[1]): for w_ in range(num_patch[0]): k_all.append(util.single2tensor4(PSF_patch[w_, h_])) k = torch.cat(k_all, dim=0) [x, k] = [el.to(device) for el in [x, k]] ab_patch = F.softplus(ab[px_start:px_start + num_patch[0], py_start:py_start + num_patch[1]]) cd = [] for h_ in range(num_patch[1]): for w_ in range(num_patch[0]): cd.append(ab_patch[w_:w_ + 1, h_]) cd = torch.cat(cd, dim=0) x_E = model.forward_patchwise(x, k, cd, num_patch, [W // gx, H // gy]) x_E = x_E[..., block_expand:block_expand + p_W, block_expand:block_expand + p_H] patch_L = patch_L_wrap.astype(np.uint8) patch_E = util.tensor2uint(x_E) t1 = time.time() print('[{}/{}]: {} s per frame'.format(img_id, len(img_names), t1 - t0)) xk = patch_E xk = xk.astype(np.uint8) cv2.imshow('res', xk) cv2.imshow('input', patch_L.astype(np.uint8)) key = cv2.waitKey(-1) if key == ord('q'): break