import cv2
import numpy as np
import os
import sys
from multiprocessing import Pool
from os import path as osp
from tqdm import tqdm
from basicsr.utils import scandir
[docs]def main():
"""A multi-thread tool to crop large images to sub-images for faster IO.
It is used for DIV2K dataset.
Args:
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 four folders to be processed for DIV2K dataset.
* DIV2K_train_HR
* DIV2K_train_LR_bicubic/X2
* DIV2K_train_LR_bicubic/X3
* DIV2K_train_LR_bicubic/X4
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'] = 20
opt['compression_level'] = 3
# HR images
opt['input_folder'] = 'datasets/DIV2K/DIV2K_train_HR'
opt['save_folder'] = 'datasets/DIV2K/DIV2K_train_HR_sub'
opt['crop_size'] = 480
opt['step'] = 240
opt['thresh_size'] = 0
extract_subimages(opt)
# LRx2 images
opt['input_folder'] = 'datasets/DIV2K/DIV2K_train_LR_bicubic/X2'
opt['save_folder'] = 'datasets/DIV2K/DIV2K_train_LR_bicubic/X2_sub'
opt['crop_size'] = 240
opt['step'] = 120
opt['thresh_size'] = 0
extract_subimages(opt)
# LRx3 images
opt['input_folder'] = 'datasets/DIV2K/DIV2K_train_LR_bicubic/X3'
opt['save_folder'] = 'datasets/DIV2K/DIV2K_train_LR_bicubic/X3_sub'
opt['crop_size'] = 160
opt['step'] = 80
opt['thresh_size'] = 0
extract_subimages(opt)
# LRx4 images
opt['input_folder'] = 'datasets/DIV2K/DIV2K_train_LR_bicubic/X4'
opt['save_folder'] = 'datasets/DIV2K/DIV2K_train_LR_bicubic/X4_sub'
opt['crop_size'] = 120
opt['step'] = 60
opt['thresh_size'] = 0
extract_subimages(opt)
[docs]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__':
main()