From 495ffc4777522e40941753e3b1b79c02f84b25b4 Mon Sep 17 00:00:00 2001 From: Grafting Rayman <156515434+GraftingRayman@users.noreply.github.com> Date: Fri, 17 Jan 2025 11:00:30 +0000 Subject: Add files via upload --- r_basicsr/data/realesrgan_paired_dataset.py | 109 ++++++++++++++++++++++++++++ 1 file changed, 109 insertions(+) create mode 100644 r_basicsr/data/realesrgan_paired_dataset.py (limited to 'r_basicsr/data/realesrgan_paired_dataset.py') diff --git a/r_basicsr/data/realesrgan_paired_dataset.py b/r_basicsr/data/realesrgan_paired_dataset.py new file mode 100644 index 0000000..a31dad1 --- /dev/null +++ b/r_basicsr/data/realesrgan_paired_dataset.py @@ -0,0 +1,109 @@ +import os +from torch.utils import data as data +from torchvision.transforms.functional import normalize + +from r_basicsr.data.data_util import paired_paths_from_folder, paired_paths_from_lmdb +from r_basicsr.data.transforms import augment, paired_random_crop +from r_basicsr.utils import FileClient, imfrombytes, img2tensor +from r_basicsr.utils.registry import DATASET_REGISTRY + + +@DATASET_REGISTRY.register(suffix='basicsr') +class RealESRGANPairedDataset(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': Use meta information file to generate paths. + If opt['io_backend'] != lmdb and opt['meta_info'] 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 (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(RealESRGANPairedDataset, self).__init__() + self.opt = opt + self.file_client = None + self.io_backend_opt = opt['io_backend'] + # mean and std for normalizing the input images + 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'] + self.filename_tmpl = opt['filename_tmpl'] if 'filename_tmpl' in opt else '{}' + + # file client (lmdb io backend) + 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' in self.opt and self.opt['meta_info'] is not None: + # disk backend with meta_info + # Each line in the meta_info describes the relative path to an image + with open(self.opt['meta_info']) as fin: + paths = [line.strip() for line in fin] + self.paths = [] + for path in paths: + gt_path, lq_path = path.split(', ') + gt_path = os.path.join(self.gt_folder, gt_path) + lq_path = os.path.join(self.lq_folder, lq_path) + self.paths.append(dict([('gt_path', gt_path), ('lq_path', lq_path)])) + else: + # disk backend + # it will scan the whole folder to get meta info + # it will be time-consuming for folders with too many files. It is recommended using an extra meta txt file + 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'] + + # Load gt and lq images. Dimension order: HWC; channel order: BGR; + # image range: [0, 1], float32. + 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) + + # augmentation for training + if self.opt['phase'] == 'train': + gt_size = self.opt['gt_size'] + # random crop + img_gt, img_lq = paired_random_crop(img_gt, img_lq, gt_size, scale, gt_path) + # flip, rotation + img_gt, img_lq = augment([img_gt, img_lq], self.opt['use_hflip'], self.opt['use_rot']) + + # BGR to RGB, HWC to CHW, numpy to tensor + img_gt, img_lq = img2tensor([img_gt, img_lq], bgr2rgb=True, float32=True) + # normalize + 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) -- cgit v1.2.3