zuenko
commented
3 years ago Closed zuenko closed 3 years ago
zuenko
commented
3 years ago 
ljdongysu
commented
3 years ago I add "self.sf = 1
img_H = img_H[0::self.sf_validation, 0::self.sf_validation, ...]
in file "/KAIR/data/dataset_usrnet.py" line 105, which dosen't matter trianing phase.Maybe it matters test phase!
anjemimini
commented
3 years ago Hi, I'm having the same problem. Did you resolve it? Thanks in advance
zuenko
commented
3 years ago @anjemimini
class DatasetUSRNet(data.Dataset):
'''
# -----------------------------------------
# Get L/k/sf/sigma for USRNet.
# Only "paths_H" and kernel is needed, synthesize L on-the-fly.
# -----------------------------------------
'''
def __init__(self, opt):
super(DatasetUSRNet, self).__init__()
self.opt = opt
self.n_channels = opt['n_channels'] if opt['n_channels'] else 3
self.patch_size = self.opt['H_size'] if self.opt['H_size'] else 96
self.sigma_max = self.opt['sigma_max'] if self.opt['sigma_max'] is not None else 25
self.scales = opt['scales'] if opt['scales'] is not None else [1,2,3,4]
self.sf_validation = opt['sf_validation'] if opt['sf_validation'] is not None else 3
#self.kernels = hdf5storage.loadmat(os.path.join('kernels', 'kernels_12.mat'))['kernels']
self.kernels = loadmat(os.path.join('kernels', 'kernels_12.mat'))['kernels'] # for validation
# -------------------
# get the path of H
# -------------------
self.paths_H = util.get_image_paths(opt['dataroot_H']) # return None if input is None
self.count = 0
def __getitem__(self, index):
# -------------------
# get H image
# -------------------
H_path = self.paths_H[index]
img_H = util.imread_uint(H_path, self.n_channels)
L_path = H_path
if self.opt['phase'] == 'train':
# ---------------------------
# 1) scale factor, ensure each batch only involves one scale factor
# ---------------------------
if self.count % self.opt['dataloader_batch_size'] == 0:
# sf = random.choice([1,2,3,4])
self.sf = random.choice(self.scales)
# self.count = 0 # optional
self.count += 1
H, W, _ = img_H.shape
# ----------------------------
# randomly crop the patch
# ----------------------------
rnd_h = random.randint(0, max(0, H - self.patch_size))
rnd_w = random.randint(0, max(0, W - self.patch_size))
patch_H = img_H[rnd_h:rnd_h + self.patch_size, rnd_w:rnd_w + self.patch_size, :]
# ---------------------------
# augmentation - flip, rotate
# ---------------------------
mode = np.random.randint(0, 8)
patch_H = util.augment_img(patch_H, mode=mode)
# ---------------------------
# 2) kernel
# ---------------------------
r_value = np.random.randint(0, 8)
if r_value>3:
k = utils_deblur.blurkernel_synthesis(h=25) # motion blur
else:
sf_k = random.choice(self.scales)
k = utils_sisr.gen_kernel(scale_factor=np.array([sf_k, sf_k])) # Gaussian blur
mode_k = np.random.randint(0, 8)
k = util.augment_img(k, mode=mode_k)
# ---------------------------
# 3) noise level
# ---------------------------
if np.random.randint(0, 8) == 1:
noise_level = 0/255.0
else:
noise_level = np.random.randint(0, self.sigma_max)/255.0
# ---------------------------
# Low-quality image
# ---------------------------
img_L = ndimage.filters.convolve(patch_H, np.expand_dims(k, axis=2), mode='wrap')
img_L = img_L[0::self.sf, 0::self.sf, ...]
# add Gaussian noise
img_L = util.uint2single(img_L) + np.random.normal(0, noise_level, img_L.shape)
img_H = patch_H
else:
self.sf = self.sf_validation
k = self.kernels[0, 0].astype(np.float64) # validation kernel
k /= np.sum(k)
noise_level = 0./255.0 # validation noise level
img_L = ndimage.filters.convolve(img_H, np.expand_dims(k, axis=2), mode='wrap') # blur
img_L = img_L[0::self.sf_validation, 0::self.sf_validation, ...] # downsampling
img_L = util.uint2single(img_L) + np.random.normal(0, noise_level, img_L.shape)
k = util.single2tensor3(np.expand_dims(np.float32(k), axis=2))
img_H, img_L = util.uint2tensor3(img_H), util.single2tensor3(img_L)
noise_level = torch.FloatTensor([noise_level]).view([1,1,1])
return {'L': img_L, 'H': img_H, 'k': k, 'sigma': noise_level, 'sf': self.sf, 'L_path': L_path, 'H_path': H_path}
def __len__(self):
return len(self.paths_H)thanks a lot :)
UESTCrookieLI
commented
3 years ago @anjemimini
class DatasetUSRNet(data.Dataset): ''' # ----------------------------------------- # Get L/k/sf/sigma for USRNet. # Only "paths_H" and kernel is needed, synthesize L on-the-fly. # ----------------------------------------- ''' def __init__(self, opt): super(DatasetUSRNet, self).__init__() self.opt = opt self.n_channels = opt['n_channels'] if opt['n_channels'] else 3 self.patch_size = self.opt['H_size'] if self.opt['H_size'] else 96 self.sigma_max = self.opt['sigma_max'] if self.opt['sigma_max'] is not None else 25 self.scales = opt['scales'] if opt['scales'] is not None else [1,2,3,4] self.sf_validation = opt['sf_validation'] if opt['sf_validation'] is not None else 3 #self.kernels = hdf5storage.loadmat(os.path.join('kernels', 'kernels_12.mat'))['kernels'] self.kernels = loadmat(os.path.join('kernels', 'kernels_12.mat'))['kernels'] # for validation # ------------------- # get the path of H # ------------------- self.paths_H = util.get_image_paths(opt['dataroot_H']) # return None if input is None self.count = 0 def __getitem__(self, index): # ------------------- # get H image # ------------------- H_path = self.paths_H[index] img_H = util.imread_uint(H_path, self.n_channels) L_path = H_path if self.opt['phase'] == 'train': # --------------------------- # 1) scale factor, ensure each batch only involves one scale factor # --------------------------- if self.count % self.opt['dataloader_batch_size'] == 0: # sf = random.choice([1,2,3,4]) self.sf = random.choice(self.scales) # self.count = 0 # optional self.count += 1 H, W, _ = img_H.shape # ---------------------------- # randomly crop the patch # ---------------------------- rnd_h = random.randint(0, max(0, H - self.patch_size)) rnd_w = random.randint(0, max(0, W - self.patch_size)) patch_H = img_H[rnd_h:rnd_h + self.patch_size, rnd_w:rnd_w + self.patch_size, :] # --------------------------- # augmentation - flip, rotate # --------------------------- mode = np.random.randint(0, 8) patch_H = util.augment_img(patch_H, mode=mode) # --------------------------- # 2) kernel # --------------------------- r_value = np.random.randint(0, 8) if r_value>3: k = utils_deblur.blurkernel_synthesis(h=25) # motion blur else: sf_k = random.choice(self.scales) k = utils_sisr.gen_kernel(scale_factor=np.array([sf_k, sf_k])) # Gaussian blur mode_k = np.random.randint(0, 8) k = util.augment_img(k, mode=mode_k) # --------------------------- # 3) noise level # --------------------------- if np.random.randint(0, 8) == 1: noise_level = 0/255.0 else: noise_level = np.random.randint(0, self.sigma_max)/255.0 # --------------------------- # Low-quality image # --------------------------- img_L = ndimage.filters.convolve(patch_H, np.expand_dims(k, axis=2), mode='wrap') img_L = img_L[0::self.sf, 0::self.sf, ...] # add Gaussian noise img_L = util.uint2single(img_L) + np.random.normal(0, noise_level, img_L.shape) img_H = patch_H else: self.sf = self.sf_validation k = self.kernels[0, 0].astype(np.float64) # validation kernel k /= np.sum(k) noise_level = 0./255.0 # validation noise level img_L = ndimage.filters.convolve(img_H, np.expand_dims(k, axis=2), mode='wrap') # blur img_L = img_L[0::self.sf_validation, 0::self.sf_validation, ...] # downsampling img_L = util.uint2single(img_L) + np.random.normal(0, noise_level, img_L.shape) k = util.single2tensor3(np.expand_dims(np.float32(k), axis=2)) img_H, img_L = util.uint2tensor3(img_H), util.single2tensor3(img_L) noise_level = torch.FloatTensor([noise_level]).view([1,1,1]) return {'L': img_L, 'H': img_H, 'k': k, 'sigma': noise_level, 'sf': self.sf, 'L_path': L_path, 'H_path': H_path} def __len__(self): return len(self.paths_H)
Hi，when I use this code, I meet another error--
could you help me? thank you very much!
UESTCrookieLI
commented
3 years ago Hi, I'm having the same problem. Did you resolve it? Thanks in advance
hi,Do you solve the error?
I replace the code with @anjemimini provided,but i meet another error like this:
can you help me? thank you!