|
from torch.utils import data as data |
|
from torchvision.transforms.functional import normalize |
|
|
|
from basicsr.data.data_util import paired_paths_from_folder, paired_paths_from_lmdb, paired_paths_from_meta_info_file |
|
from basicsr.data.transforms import augment, paired_random_crop |
|
from basicsr.utils import FileClient, bgr2ycbcr, imfrombytes, img2tensor |
|
from basicsr.utils.registry import DATASET_REGISTRY |
|
|
|
|
|
@DATASET_REGISTRY.register() |
|
class PairedImageDataset(data.Dataset): |
|
"""Paired image dataset for image restoration. |
|
|
|
Read LQ (Low Quality, e.g. LR (Low Resolution), blurry, noisy, etc) and GT image pairs. |
|
|
|
There are three modes: |
|
|
|
1. **lmdb**: Use lmdb files. If opt['io_backend'] == lmdb. |
|
2. **meta_info_file**: Use meta information file to generate paths. \ |
|
If opt['io_backend'] != lmdb and opt['meta_info_file'] is not None. |
|
3. **folder**: Scan folders to generate paths. The rest. |
|
|
|
Args: |
|
opt (dict): Config for train datasets. It contains the following keys: |
|
dataroot_gt (str): Data root path for gt. |
|
dataroot_lq (str): Data root path for lq. |
|
meta_info_file (str): Path for meta information file. |
|
io_backend (dict): IO backend type and other kwarg. |
|
filename_tmpl (str): Template for each filename. Note that the template excludes the file extension. |
|
Default: '{}'. |
|
gt_size (int): Cropped patched size for gt patches. |
|
use_hflip (bool): Use horizontal flips. |
|
use_rot (bool): Use rotation (use vertical flip and transposing h and w for implementation). |
|
scale (bool): Scale, which will be added automatically. |
|
phase (str): 'train' or 'val'. |
|
""" |
|
|
|
def __init__(self, opt): |
|
super(PairedImageDataset, self).__init__() |
|
self.opt = opt |
|
|
|
self.file_client = None |
|
self.io_backend_opt = opt['io_backend'] |
|
self.mean = opt['mean'] if 'mean' in opt else None |
|
self.std = opt['std'] if 'std' in opt else None |
|
|
|
self.gt_folder, self.lq_folder = opt['dataroot_gt'], opt['dataroot_lq'] |
|
if 'filename_tmpl' in opt: |
|
self.filename_tmpl = opt['filename_tmpl'] |
|
else: |
|
self.filename_tmpl = '{}' |
|
|
|
if self.io_backend_opt['type'] == 'lmdb': |
|
self.io_backend_opt['db_paths'] = [self.lq_folder, self.gt_folder] |
|
self.io_backend_opt['client_keys'] = ['lq', 'gt'] |
|
self.paths = paired_paths_from_lmdb([self.lq_folder, self.gt_folder], ['lq', 'gt']) |
|
elif 'meta_info_file' in self.opt and self.opt['meta_info_file'] is not None: |
|
self.paths = paired_paths_from_meta_info_file([self.lq_folder, self.gt_folder], ['lq', 'gt'], |
|
self.opt['meta_info_file'], self.filename_tmpl) |
|
else: |
|
self.paths = paired_paths_from_folder([self.lq_folder, self.gt_folder], ['lq', 'gt'], self.filename_tmpl) |
|
|
|
def __getitem__(self, index): |
|
if self.file_client is None: |
|
self.file_client = FileClient(self.io_backend_opt.pop('type'), **self.io_backend_opt) |
|
|
|
scale = self.opt['scale'] |
|
|
|
|
|
|
|
gt_path = self.paths[index]['gt_path'] |
|
img_bytes = self.file_client.get(gt_path, 'gt') |
|
img_gt = imfrombytes(img_bytes, float32=True) |
|
lq_path = self.paths[index]['lq_path'] |
|
img_bytes = self.file_client.get(lq_path, 'lq') |
|
img_lq = imfrombytes(img_bytes, float32=True) |
|
|
|
|
|
if self.opt['phase'] == 'train': |
|
gt_size = self.opt['gt_size'] |
|
|
|
img_gt, img_lq = paired_random_crop(img_gt, img_lq, gt_size, scale, gt_path) |
|
|
|
img_gt, img_lq = augment([img_gt, img_lq], self.opt['use_hflip'], self.opt['use_rot']) |
|
|
|
|
|
if 'color' in self.opt and self.opt['color'] == 'y': |
|
img_gt = bgr2ycbcr(img_gt, y_only=True)[..., None] |
|
img_lq = bgr2ycbcr(img_lq, y_only=True)[..., None] |
|
|
|
|
|
|
|
if self.opt['phase'] != 'train': |
|
img_gt = img_gt[0:img_lq.shape[0] * scale, 0:img_lq.shape[1] * scale, :] |
|
|
|
|
|
img_gt, img_lq = img2tensor([img_gt, img_lq], bgr2rgb=True, float32=True) |
|
|
|
if self.mean is not None or self.std is not None: |
|
normalize(img_lq, self.mean, self.std, inplace=True) |
|
normalize(img_gt, self.mean, self.std, inplace=True) |
|
|
|
return {'lq': img_lq, 'gt': img_gt, 'lq_path': lq_path, 'gt_path': gt_path} |
|
|
|
def __len__(self): |
|
return len(self.paths) |
|
|