NAFNet/scripts/data_preparation/sidd.py

122 lines
3.9 KiB
Python

# ------------------------------------------------------------------------
# Copyright (c) 2022 megvii-model. All Rights Reserved.
# ------------------------------------------------------------------------
# Modified from BasicSR (https://github.com/xinntao/BasicSR)
# Copyright 2018-2020 BasicSR Authors
# ------------------------------------------------------------------------
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_SIDD
from basicsr.utils.create_lmdb import create_lmdb_for_SIDD
def main():
opt = {}
opt['n_thread'] = 20
opt['compression_level'] = 3
opt['input_folder'] = './datasets/SIDD/Data'
opt['save_folder'] = './datasets/SIDD/train/input_crops'
opt['crop_size'] = 512
opt['step'] = 384
opt['thresh_size'] = 0
opt['keywords'] = '_NOISY'
extract_subimages(opt)
opt['save_folder'] = './datasets/SIDD/train/gt_crops'
opt['keywords'] = '_GT'
extract_subimages(opt)
create_lmdb_for_SIDD()
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)
img_list = list(scandir_SIDD(input_folder, keywords=opt['keywords'], recursive=True, 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))
img_name = img_name.replace(opt['keywords'], '')
img = cv2.imread(path, cv2.IMREAD_UNCHANGED)
if img.ndim == 2:
h, w = img.shape
elif img.ndim == 3:
h, w, c = img.shape
else:
raise ValueError(f'Image ndim should be 2 or 3, but got {img.ndim}')
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()
# ... make sidd to lmdb