First commit.

realesrgan/train.py

+# flake8: noqa
+import os.path as osp
+from basicsr.train import train_pipeline
+
+import realesrgan.archs
+import realesrgan.data
+import realesrgan.models
+
+if __name__ == '__main__':
+    root_path = osp.abspath(osp.join(__file__, osp.pardir, osp.pardir))
+    train_pipeline(root_path)

realesrgan/utils.py

+import cv2
+import math
+import numpy as np
+import os
+import queue
+import threading
+import torch
+from basicsr.utils.download_util import load_file_from_url
+from torch.nn import functional as F
+
+ROOT_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+
+
+class RealESRGANer():
+    """A helper class for upsampling images with RealESRGAN.
+
+    Args:
+        scale (int): Upsampling scale factor used in the networks. It is usually 2 or 4.
+        model_path (str): The path to the pretrained model. It can be urls (will first download it automatically).
+        model (nn.Module): The defined network. Default: None.
+        tile (int): As too large images result in the out of GPU memory issue, so this tile option will first crop
+            input images into tiles, and then process each of them. Finally, they will be merged into one image.
+            0 denotes for do not use tile. Default: 0.
+        tile_pad (int): The pad size for each tile, to remove border artifacts. Default: 10.
+        pre_pad (int): Pad the input images to avoid border artifacts. Default: 10.
+        half (float): Whether to use half precision during inference. Default: False.
+    """
+
+    def __init__(self,
+                 scale,
+                 model_path,
+                 dni_weight=None,
+                 model=None,
+                 tile=0,
+                 tile_pad=10,
+                 pre_pad=10,
+                 half=False,
+                 device=None,
+                 gpu_id=None):
+        self.scale = scale
+        self.tile_size = tile
+        self.tile_pad = tile_pad
+        self.pre_pad = pre_pad
+        self.mod_scale = None
+        self.half = half
+
+        # initialize model
+        if gpu_id:
+            self.device = torch.device(
+                f'cuda:{gpu_id}' if torch.cuda.is_available() else 'cpu') if device is None else device
+        else:
+            self.device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') if device is None else device
+
+        if isinstance(model_path, list):
+            # dni
+            assert len(model_path) == len(dni_weight), 'model_path and dni_weight should have the save length.'
+            loadnet = self.dni(model_path[0], model_path[1], dni_weight)
+        else:
+            # if the model_path starts with https, it will first download models to the folder: weights
+            if model_path.startswith('https://'):
+                model_path = load_file_from_url(
+                    url=model_path, model_dir=os.path.join(ROOT_DIR, 'weights'), progress=True, file_name=None)
+            loadnet = torch.load(model_path, map_location=torch.device('cpu'))
+
+        # prefer to use params_ema
+        if 'params_ema' in loadnet:
+            keyname = 'params_ema'
+        else:
+            keyname = 'params'
+        model.load_state_dict(loadnet[keyname], strict=True)
+
+        model.eval()
+        self.model = model.to(self.device)
+        if self.half:
+            self.model = self.model.half()
+
+    def dni(self, net_a, net_b, dni_weight, key='params', loc='cpu'):
+        """Deep network interpolation.
+
+        ``Paper: Deep Network Interpolation for Continuous Imagery Effect Transition``
+        """
+        net_a = torch.load(net_a, map_location=torch.device(loc))
+        net_b = torch.load(net_b, map_location=torch.device(loc))
+        for k, v_a in net_a[key].items():
+            net_a[key][k] = dni_weight[0] * v_a + dni_weight[1] * net_b[key][k]
+        return net_a
+
+    def pre_process(self, img):
+        """Pre-process, such as pre-pad and mod pad, so that the images can be divisible
+        """
+        img = torch.from_numpy(np.transpose(img, (2, 0, 1))).float()
+        self.img = img.unsqueeze(0).to(self.device)
+        if self.half:
+            self.img = self.img.half()
+
+        # pre_pad
+        if self.pre_pad != 0:
+            self.img = F.pad(self.img, (0, self.pre_pad, 0, self.pre_pad), 'reflect')
+        # mod pad for divisible borders
+        if self.scale == 2:
+            self.mod_scale = 2
+        elif self.scale == 1:
+            self.mod_scale = 4
+        if self.mod_scale is not None:
+            self.mod_pad_h, self.mod_pad_w = 0, 0
+            _, _, h, w = self.img.size()
+            if (h % self.mod_scale != 0):
+                self.mod_pad_h = (self.mod_scale - h % self.mod_scale)
+            if (w % self.mod_scale != 0):
+                self.mod_pad_w = (self.mod_scale - w % self.mod_scale)
+            self.img = F.pad(self.img, (0, self.mod_pad_w, 0, self.mod_pad_h), 'reflect')
+
+    def process(self):
+        # model inference
+        self.output = self.model(self.img)
+
+    def tile_process(self):
+        """It will first crop input images to tiles, and then process each tile.
+        Finally, all the processed tiles are merged into one images.
+
+        Modified from: https://github.com/ata4/esrgan-launcher
+        """
+        batch, channel, height, width = self.img.shape
+        output_height = height * self.scale
+        output_width = width * self.scale
+        output_shape = (batch, channel, output_height, output_width)
+
+        # start with black image
+        self.output = self.img.new_zeros(output_shape)
+        tiles_x = math.ceil(width / self.tile_size)
+        tiles_y = math.ceil(height / self.tile_size)
+
+        # loop over all tiles
+        for y in range(tiles_y):
+            for x in range(tiles_x):
+                # extract tile from input image
+                ofs_x = x * self.tile_size
+                ofs_y = y * self.tile_size
+                # input tile area on total image
+                input_start_x = ofs_x
+                input_end_x = min(ofs_x + self.tile_size, width)
+                input_start_y = ofs_y
+                input_end_y = min(ofs_y + self.tile_size, height)
+
+                # input tile area on total image with padding
+                input_start_x_pad = max(input_start_x - self.tile_pad, 0)
+                input_end_x_pad = min(input_end_x + self.tile_pad, width)
+                input_start_y_pad = max(input_start_y - self.tile_pad, 0)
+                input_end_y_pad = min(input_end_y + self.tile_pad, height)
+
+                # input tile dimensions
+                input_tile_width = input_end_x - input_start_x
+                input_tile_height = input_end_y - input_start_y
+                tile_idx = y * tiles_x + x + 1
+                input_tile = self.img[:, :, input_start_y_pad:input_end_y_pad, input_start_x_pad:input_end_x_pad]
+
+                # upscale tile
+                try:
+                    with torch.no_grad():
+                        output_tile = self.model(input_tile)
+                except RuntimeError as error:
+                    print('Error', error)
+                print(f'\tTile {tile_idx}/{tiles_x * tiles_y}')
+
+                # output tile area on total image
+                output_start_x = input_start_x * self.scale
+                output_end_x = input_end_x * self.scale
+                output_start_y = input_start_y * self.scale
+                output_end_y = input_end_y * self.scale
+
+                # output tile area without padding
+                output_start_x_tile = (input_start_x - input_start_x_pad) * self.scale
+                output_end_x_tile = output_start_x_tile + input_tile_width * self.scale
+                output_start_y_tile = (input_start_y - input_start_y_pad) * self.scale
+                output_end_y_tile = output_start_y_tile + input_tile_height * self.scale
+
+                # put tile into output image
+                self.output[:, :, output_start_y:output_end_y,
+                            output_start_x:output_end_x] = output_tile[:, :, output_start_y_tile:output_end_y_tile,
+                                                                       output_start_x_tile:output_end_x_tile]
+
+    def post_process(self):
+        # remove extra pad
+        if self.mod_scale is not None:
+            _, _, h, w = self.output.size()
+            self.output = self.output[:, :, 0:h - self.mod_pad_h * self.scale, 0:w - self.mod_pad_w * self.scale]
+        # remove prepad
+        if self.pre_pad != 0:
+            _, _, h, w = self.output.size()
+            self.output = self.output[:, :, 0:h - self.pre_pad * self.scale, 0:w - self.pre_pad * self.scale]
+        return self.output
+
+    @torch.no_grad()
+    def enhance(self, img, outscale=None, alpha_upsampler='realesrgan'):
+        h_input, w_input = img.shape[0:2]
+        # img: numpy
+        img = img.astype(np.float32)
+        if np.max(img) > 256:  # 16-bit image
+            max_range = 65535
+            print('\tInput is a 16-bit image')
+        else:
+            max_range = 255
+        img = img / max_range
+        if len(img.shape) == 2:  # gray image
+            img_mode = 'L'
+            img = cv2.cvtColor(img, cv2.COLOR_GRAY2RGB)
+        elif img.shape[2] == 4:  # RGBA image with alpha channel
+            img_mode = 'RGBA'
+            alpha = img[:, :, 3]
+            img = img[:, :, 0:3]
+            img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
+            if alpha_upsampler == 'realesrgan':
+                alpha = cv2.cvtColor(alpha, cv2.COLOR_GRAY2RGB)
+        else:
+            img_mode = 'RGB'
+            img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
+
+        # ------------------- process image (without the alpha channel) ------------------- #
+        self.pre_process(img)
+        if self.tile_size > 0:
+            self.tile_process()
+        else:
+            self.process()
+        output_img = self.post_process()
+        output_img = output_img.data.squeeze().float().cpu().clamp_(0, 1).numpy()
+        output_img = np.transpose(output_img[[2, 1, 0], :, :], (1, 2, 0))
+        if img_mode == 'L':
+            output_img = cv2.cvtColor(output_img, cv2.COLOR_BGR2GRAY)
+
+        # ------------------- process the alpha channel if necessary ------------------- #
+        if img_mode == 'RGBA':
+            if alpha_upsampler == 'realesrgan':
+                self.pre_process(alpha)
+                if self.tile_size > 0:
+                    self.tile_process()
+                else:
+                    self.process()
+                output_alpha = self.post_process()
+                output_alpha = output_alpha.data.squeeze().float().cpu().clamp_(0, 1).numpy()
+                output_alpha = np.transpose(output_alpha[[2, 1, 0], :, :], (1, 2, 0))
+                output_alpha = cv2.cvtColor(output_alpha, cv2.COLOR_BGR2GRAY)
+            else:  # use the cv2 resize for alpha channel
+                h, w = alpha.shape[0:2]
+                output_alpha = cv2.resize(alpha, (w * self.scale, h * self.scale), interpolation=cv2.INTER_LINEAR)
+
+            # merge the alpha channel
+            output_img = cv2.cvtColor(output_img, cv2.COLOR_BGR2BGRA)
+            output_img[:, :, 3] = output_alpha
+
+        # ------------------------------ return ------------------------------ #
+        if max_range == 65535:  # 16-bit image
+            output = (output_img * 65535.0).round().astype(np.uint16)
+        else:
+            output = (output_img * 255.0).round().astype(np.uint8)
+
+        if outscale is not None and outscale != float(self.scale):
+            output = cv2.resize(
+                output, (
+                    int(w_input * outscale),
+                    int(h_input * outscale),
+                ), interpolation=cv2.INTER_LANCZOS4)
+
+        return output, img_mode
+
+
+class PrefetchReader(threading.Thread):
+    """Prefetch images.
+
+    Args:
+        img_list (list[str]): A image list of image paths to be read.
+        num_prefetch_queue (int): Number of prefetch queue.
+    """
+
+    def __init__(self, img_list, num_prefetch_queue):
+        super().__init__()
+        self.que = queue.Queue(num_prefetch_queue)
+        self.img_list = img_list
+
+    def run(self):
+        for img_path in self.img_list:
+            img = cv2.imread(img_path, cv2.IMREAD_UNCHANGED)
+            self.que.put(img)
+
+        self.que.put(None)
+
+    def __next__(self):
+        next_item = self.que.get()
+        if next_item is None:
+            raise StopIteration
+        return next_item
+
+    def __iter__(self):
+        return self
+
+
+class IOConsumer(threading.Thread):
+
+    def __init__(self, opt, que, qid):
+        super().__init__()
+        self._queue = que
+        self.qid = qid
+        self.opt = opt
+
+    def run(self):
+        while True:
+            msg = self._queue.get()
+            if isinstance(msg, str) and msg == 'quit':
+                break
+
+            output = msg['output']
+            save_path = msg['save_path']
+            cv2.imwrite(save_path, output)
+        print(f'IO worker {self.qid} is done.')

requirements.txt

+basicsr>=1.4.2
+facexlib>=0.2.5
+gfpgan>=1.3.5
+numpy
+opencv-python==4.9.0.80
+Pillow
+torch>=1.7
+torchvision
+tqdm
+scipy==1.10.1
+scikit-image
+tb-nightly
\ No newline at end of file

scripts/extract_subimages.py

+import argparse
+import cv2
+import numpy as np
+import os
+import sys
+from basicsr.utils import scandir
+from multiprocessing import Pool
+from os import path as osp
+from tqdm import tqdm
+
+
+def main(args):
+    """A multi-thread tool to crop large images to sub-images for faster IO.
+
+    opt (dict): Configuration dict. It contains:
+        n_thread (int): Thread number.
+        compression_level (int):  CV_IMWRITE_PNG_COMPRESSION from 0 to 9. A higher value means a smaller size
+            and longer compression time. Use 0 for faster CPU decompression. Default: 3, same in cv2.
+        input_folder (str): Path to the input folder.
+        save_folder (str): Path to save folder.
+        crop_size (int): Crop size.
+        step (int): Step for overlapped sliding window.
+        thresh_size (int): Threshold size. Patches whose size is lower than thresh_size will be dropped.
+
+    Usage:
+        For each folder, run this script.
+        Typically, there are GT folder and LQ folder to be processed for DIV2K dataset.
+        After process, each sub_folder should have the same number of subimages.
+        Remember to modify opt configurations according to your settings.
+    """
+
+    opt = {}
+    opt['n_thread'] = args.n_thread
+    opt['compression_level'] = args.compression_level
+    opt['input_folder'] = args.input
+    opt['save_folder'] = args.output
+    opt['crop_size'] = args.crop_size
+    opt['step'] = args.step
+    opt['thresh_size'] = args.thresh_size
+    extract_subimages(opt)
+
+
+def extract_subimages(opt):
+    """Crop images to subimages.
+
+    Args:
+        opt (dict): Configuration dict. It contains:
+            input_folder (str): Path to the input folder.
+            save_folder (str): Path to save folder.
+            n_thread (int): Thread number.
+    """
+    input_folder = opt['input_folder']
+    save_folder = opt['save_folder']
+    if not osp.exists(save_folder):
+        os.makedirs(save_folder)
+        print(f'mkdir {save_folder} ...')
+    else:
+        print(f'Folder {save_folder} already exists. Exit.')
+        sys.exit(1)
+
+    # scan all images
+    img_list = list(scandir(input_folder, full_path=True))
+
+    pbar = tqdm(total=len(img_list), unit='image', desc='Extract')
+    pool = Pool(opt['n_thread'])
+    for path in img_list:
+        pool.apply_async(worker, args=(path, opt), callback=lambda arg: pbar.update(1))
+    pool.close()
+    pool.join()
+    pbar.close()
+    print('All processes done.')
+
+
+def worker(path, opt):
+    """Worker for each process.
+
+    Args:
+        path (str): Image path.
+        opt (dict): Configuration dict. It contains:
+            crop_size (int): Crop size.
+            step (int): Step for overlapped sliding window.
+            thresh_size (int): Threshold size. Patches whose size is lower than thresh_size will be dropped.
+            save_folder (str): Path to save folder.
+            compression_level (int): for cv2.IMWRITE_PNG_COMPRESSION.
+
+    Returns:
+        process_info (str): Process information displayed in progress bar.
+    """
+    crop_size = opt['crop_size']
+    step = opt['step']
+    thresh_size = opt['thresh_size']
+    img_name, extension = osp.splitext(osp.basename(path))
+
+    # remove the x2, x3, x4 and x8 in the filename for DIV2K
+    img_name = img_name.replace('x2', '').replace('x3', '').replace('x4', '').replace('x8', '')
+
+    img = cv2.imread(path, cv2.IMREAD_UNCHANGED)
+
+    h, w = img.shape[0:2]
+    h_space = np.arange(0, h - crop_size + 1, step)
+    if h - (h_space[-1] + crop_size) > thresh_size:
+        h_space = np.append(h_space, h - crop_size)
+    w_space = np.arange(0, w - crop_size + 1, step)
+    if w - (w_space[-1] + crop_size) > thresh_size:
+        w_space = np.append(w_space, w - crop_size)
+
+    index = 0
+    for x in h_space:
+        for y in w_space:
+            index += 1
+            cropped_img = img[x:x + crop_size, y:y + crop_size, ...]
+            cropped_img = np.ascontiguousarray(cropped_img)
+            cv2.imwrite(
+                osp.join(opt['save_folder'], f'{img_name}_s{index:03d}{extension}'), cropped_img,
+                [cv2.IMWRITE_PNG_COMPRESSION, opt['compression_level']])
+    process_info = f'Processing {img_name} ...'
+    return process_info
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--input', type=str, default='datasets/DF2K/DF2K_HR', help='Input folder')
+    parser.add_argument('--output', type=str, default='datasets/DF2K/DF2K_HR_sub', help='Output folder')
+    parser.add_argument('--crop_size', type=int, default=480, help='Crop size')
+    parser.add_argument('--step', type=int, default=240, help='Step for overlapped sliding window')
+    parser.add_argument(
+        '--thresh_size',
+        type=int,
+        default=0,
+        help='Threshold size. Patches whose size is lower than thresh_size will be dropped.')
+    parser.add_argument('--n_thread', type=int, default=20, help='Thread number.')
+    parser.add_argument('--compression_level', type=int, default=3, help='Compression level')
+    args = parser.parse_args()
+
+    main(args)

scripts/generate_meta_info.py

+import argparse
+import cv2
+import glob
+import os
+
+
+def main(args):
+    txt_file = open(args.meta_info, 'w')
+    for folder, root in zip(args.input, args.root):
+        img_paths = sorted(glob.glob(os.path.join(folder, '*')))
+        for img_path in img_paths:
+            status = True
+            if args.check:
+                # read the image once for check, as some images may have errors
+                try:
+                    img = cv2.imread(img_path)
+                except (IOError, OSError) as error:
+                    print(f'Read {img_path} error: {error}')
+                    status = False
+                if img is None:
+                    status = False
+                    print(f'Img is None: {img_path}')
+            if status:
+                # get the relative path
+                img_name = os.path.relpath(img_path, root)
+                print(img_name)
+                txt_file.write(f'{img_name}\n')
+
+
+if __name__ == '__main__':
+    """Generate meta info (txt file) for only Ground-Truth images.
+
+    It can also generate meta info from several folders into one txt file.
+    """
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        '--input',
+        nargs='+',
+        default=['datasets/DF2K/DF2K_HR', 'datasets/DF2K/DF2K_multiscale'],
+        help='Input folder, can be a list')
+    parser.add_argument(
+        '--root',
+        nargs='+',
+        default=['datasets/DF2K', 'datasets/DF2K'],
+        help='Folder root, should have the length as input folders')
+    parser.add_argument(
+        '--meta_info',
+        type=str,
+        default='datasets/DF2K/meta_info/meta_info_DF2Kmultiscale.txt',
+        help='txt path for meta info')
+    parser.add_argument('--check', action='store_true', help='Read image to check whether it is ok')
+    args = parser.parse_args()
+
+    assert len(args.input) == len(args.root), ('Input folder and folder root should have the same length, but got '
+                                               f'{len(args.input)} and {len(args.root)}.')
+    os.makedirs(os.path.dirname(args.meta_info), exist_ok=True)
+
+    main(args)

scripts/generate_meta_info_pairdata.py

+import argparse
+import glob
+import os
+
+
+def main(args):
+    txt_file = open(args.meta_info, 'w')
+    # sca images
+    img_paths_gt = sorted(glob.glob(os.path.join(args.input[0], '*')))
+    img_paths_lq = sorted(glob.glob(os.path.join(args.input[1], '*')))
+
+    assert len(img_paths_gt) == len(img_paths_lq), ('GT folder and LQ folder should have the same length, but got '
+                                                    f'{len(img_paths_gt)} and {len(img_paths_lq)}.')
+
+    for img_path_gt, img_path_lq in zip(img_paths_gt, img_paths_lq):
+        # get the relative paths
+        img_name_gt = os.path.relpath(img_path_gt, args.root[0])
+        img_name_lq = os.path.relpath(img_path_lq, args.root[1])
+        print(f'{img_name_gt}, {img_name_lq}')
+        txt_file.write(f'{img_name_gt}, {img_name_lq}\n')
+
+
+if __name__ == '__main__':
+    """This script is used to generate meta info (txt file) for paired images.
+    """
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        '--input',
+        nargs='+',
+        default=['datasets/DF2K/DIV2K_train_HR_sub', 'datasets/DF2K/DIV2K_train_LR_bicubic_X4_sub'],
+        help='Input folder, should be [gt_folder, lq_folder]')
+    parser.add_argument('--root', nargs='+', default=[None, None], help='Folder root, will use the ')
+    parser.add_argument(
+        '--meta_info',
+        type=str,
+        default='datasets/DF2K/meta_info/meta_info_DIV2K_sub_pair.txt',
+        help='txt path for meta info')
+    args = parser.parse_args()
+
+    assert len(args.input) == 2, 'Input folder should have two elements: gt folder and lq folder'
+    assert len(args.root) == 2, 'Root path should have two elements: root for gt folder and lq folder'
+    os.makedirs(os.path.dirname(args.meta_info), exist_ok=True)
+    for i in range(2):
+        if args.input[i].endswith('/'):
+            args.input[i] = args.input[i][:-1]
+        if args.root[i] is None:
+            args.root[i] = os.path.dirname(args.input[i])
+
+    main(args)

scripts/generate_multiscale_DF2K.py

+import argparse
+import glob
+import os
+from PIL import Image
+
+
+def main(args):
+    # For DF2K, we consider the following three scales,
+    # and the smallest image whose shortest edge is 400
+    scale_list = [0.75, 0.5, 1 / 3]
+    shortest_edge = 400
+
+    path_list = sorted(glob.glob(os.path.join(args.input, '*')))
+    for path in path_list:
+        print(path)
+        basename = os.path.splitext(os.path.basename(path))[0]
+
+        img = Image.open(path)
+        width, height = img.size
+        for idx, scale in enumerate(scale_list):
+            print(f'\t{scale:.2f}')
+            rlt = img.resize((int(width * scale), int(height * scale)), resample=Image.LANCZOS)
+            rlt.save(os.path.join(args.output, f'{basename}T{idx}.png'))
+
+        # save the smallest image which the shortest edge is 400
+        if width < height:
+            ratio = height / width
+            width = shortest_edge
+            height = int(width * ratio)
+        else:
+            ratio = width / height
+            height = shortest_edge
+            width = int(height * ratio)
+        rlt = img.resize((int(width), int(height)), resample=Image.LANCZOS)
+        rlt.save(os.path.join(args.output, f'{basename}T{idx+1}.png'))
+
+
+if __name__ == '__main__':
+    """Generate multi-scale versions for GT images with LANCZOS resampling.
+    It is now used for DF2K dataset (DIV2K + Flickr 2K)
+    """
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--input', type=str, default='datasets/DF2K/DF2K_HR', help='Input folder')
+    parser.add_argument('--output', type=str, default='datasets/DF2K/DF2K_multiscale', help='Output folder')
+    args = parser.parse_args()
+
+    os.makedirs(args.output, exist_ok=True)
+    main(args)

scripts/pytorch2onnx.py

+import argparse
+import torch
+import torch.onnx
+from basicsr.archs.rrdbnet_arch import RRDBNet
+
+
+def main(args):
+    # An instance of the model
+    model = RRDBNet(num_in_ch=3, num_out_ch=3, num_feat=64, num_block=23, num_grow_ch=32, scale=4)
+    if args.params:
+        keyname = 'params'
+    else:
+        keyname = 'params_ema'
+    model.load_state_dict(torch.load(args.input)[keyname])
+    # set the train mode to false since we will only run the forward pass.
+    model.train(False)
+    model.cpu().eval()
+
+    # An example input
+    x = torch.rand(1, 3, 64, 64)
+    # Export the model
+    with torch.no_grad():
+        torch_out = torch.onnx._export(model, x, args.output, opset_version=11, export_params=True)
+    print(torch_out.shape)
+
+
+if __name__ == '__main__':
+    """Convert pytorch model to onnx models"""
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        '--input', type=str, default='experiments/pretrained_models/RealESRGAN_x4plus.pth', help='Input model path')
+    parser.add_argument('--output', type=str, default='realesrgan-x4.onnx', help='Output onnx path')
+    parser.add_argument('--params', action='store_false', help='Use params instead of params_ema')
+    args = parser.parse_args()
+
+    main(args)

setup.cfg

+[flake8]
+ignore =
+    # line break before binary operator (W503)
+    W503,
+    # line break after binary operator (W504)
+    W504,
+max-line-length=120
+
+[yapf]
+based_on_style = pep8
+column_limit = 120
+blank_line_before_nested_class_or_def = true
+split_before_expression_after_opening_paren = true
+
+[isort]
+line_length = 120
+multi_line_output = 0
+known_standard_library = pkg_resources,setuptools
+known_first_party = realesrgan
+known_third_party = PIL,basicsr,cv2,numpy,pytest,torch,torchvision,tqdm,yaml
+no_lines_before = STDLIB,LOCALFOLDER
+default_section = THIRDPARTY
+
+[codespell]
+skip = .git,./docs/build
+count =
+quiet-level = 3
+
+[aliases]
+test=pytest
+
+[tool:pytest]
+addopts=tests/

setup.py

+#!/usr/bin/env python
+
+from setuptools import find_packages, setup
+
+import os
+import subprocess
+import time
+
+version_file = 'realesrgan/version.py'
+
+
+def readme():
+    with open('README.md', encoding='utf-8') as f:
+        content = f.read()
+    return content
+
+
+def get_git_hash():
+
+    def _minimal_ext_cmd(cmd):
+        # construct minimal environment
+        env = {}
+        for k in ['SYSTEMROOT', 'PATH', 'HOME']:
+            v = os.environ.get(k)
+            if v is not None:
+                env[k] = v
+        # LANGUAGE is used on win32
+        env['LANGUAGE'] = 'C'
+        env['LANG'] = 'C'
+        env['LC_ALL'] = 'C'
+        out = subprocess.Popen(cmd, stdout=subprocess.PIPE, env=env).communicate()[0]
+        return out
+
+    try:
+        out = _minimal_ext_cmd(['git', 'rev-parse', 'HEAD'])
+        sha = out.strip().decode('ascii')
+    except OSError:
+        sha = 'unknown'
+
+    return sha
+
+
+def get_hash():
+    if os.path.exists('.git'):
+        sha = get_git_hash()[:7]
+    else:
+        sha = 'unknown'
+
+    return sha
+
+
+def write_version_py():
+    content = """# GENERATED VERSION FILE
+# TIME: {}
+__version__ = '{}'
+__gitsha__ = '{}'
+version_info = ({})
+"""
+    sha = get_hash()
+    with open('VERSION', 'r') as f:
+        SHORT_VERSION = f.read().strip()
+    VERSION_INFO = ', '.join([x if x.isdigit() else f'"{x}"' for x in SHORT_VERSION.split('.')])
+
+    version_file_str = content.format(time.asctime(), SHORT_VERSION, sha, VERSION_INFO)
+    with open(version_file, 'w') as f:
+        f.write(version_file_str)
+
+
+def get_version():
+    with open(version_file, 'r') as f:
+        exec(compile(f.read(), version_file, 'exec'))
+    return locals()['__version__']
+
+
+def get_requirements(filename='requirements.txt'):
+    here = os.path.dirname(os.path.realpath(__file__))
+    with open(os.path.join(here, filename), 'r') as f:
+        requires = [line.replace('\n', '') for line in f.readlines()]
+    return requires
+
+
+if __name__ == '__main__':
+    write_version_py()
+    setup(
+        name='realesrgan',
+        version=get_version(),
+        description='Real-ESRGAN aims at developing Practical Algorithms for General Image Restoration',
+        long_description=readme(),
+        long_description_content_type='text/markdown',
+        author='Xintao Wang',
+        author_email='xintao.wang@outlook.com',
+        keywords='computer vision, pytorch, image restoration, super-resolution, esrgan, real-esrgan',
+        url='https://github.com/xinntao/Real-ESRGAN',
+        include_package_data=True,
+        packages=find_packages(exclude=('options', 'datasets', 'experiments', 'results', 'tb_logger', 'wandb')),
+        classifiers=[
+            'Development Status :: 4 - Beta',
+            'License :: OSI Approved :: Apache Software License',
+            'Operating System :: OS Independent',
+            'Programming Language :: Python :: 3',
+            'Programming Language :: Python :: 3.7',
+            'Programming Language :: Python :: 3.8',
+        ],
+        license='BSD-3-Clause License',
+        setup_requires=['cython', 'numpy'],
+        install_requires=get_requirements(),
+        zip_safe=False)

tests/data/gt.lmdb/meta_info.txt

+baboon.png (480,500,3) 1
+comic.png (360,240,3) 1

tests/data/lq.lmdb/meta_info.txt

+baboon.png (120,125,3) 1
+comic.png (80,60,3) 1