def crop(save_gt_path, json_path, save_path):
if os.path.exists(save_path):
shutil.rmtree(save_path, ignore_errors=True)
os.makedirs(save_path, exist_ok=True)
data = load_gt(json_path)
file_list = []
for img_path, gt in tqdm(data.items()):
img = Image.open(img_path).convert('RGB')
img_name = pathlib.Path(img_path).stem
for i, (polygon, text, illegibility, language) in enumerate(
zip(gt['polygons'], gt['texts'], gt['illegibility_list'],
gt['language_list'])):
if illegibility:
continue
polygon = np.array(polygon)
roi_img_save_path = os.path.join(save_path,
'{}_{}.jpg'.format(img_name, i))
# 对于只有四个点的图片，反射变换后存储
if len(polygon) == 4:
np_img = np.asarray(img)
roi_img = four_point_transform(np_img, polygon)
roi_img = Image.fromarray(roi_img).convert('RGB')
else:
x_min = polygon[:, 0].min()
x_max = polygon[:, 0].max()
y_min = polygon[:, 1].min()
y_max = polygon[:, 1].max()
roi_img = img.crop((x_min, y_min, x_max, y_max))
roi_img.save(roi_img_save_path)
file_list.append(roi_img_save_path + '\t' + text + '\t' + language)
# plt.title(text)
# plt.imshow(roi_img)
# plt.show()
save(file_list, save_gt_path)
# -*- coding: utf-8 -*-
# @Time : 2020/3/20 20:33
# @Author : zhoujun
"""
用于检查生成的json文件有没有问题
"""
from PIL import Image
from tqdm import tqdm
from matplotlib import pyplot as plt
from convert.utils import show_bbox_on_image, load_gt
if __name__ == '__main__':
json_path = r'D:\dataset\自然场景文字检测挑战赛初赛数据\验证集\validation_new.json'
data = load_gt(json_path)
for img_path, gt in tqdm(data.items()):
# print(gt['illegibility_list'])
# print(gt['texts'])
img = Image.open(img_path)
img = show_bbox_on_image(img, gt['polygons'], gt['texts'])
plt.imshow(img)
plt.show()
env.close()
print('Created dataset with %d samples' % nSamples)
def show_demo(demo_number, image_path_list, label_list):
print('\nShow some demo to prevent creating wrong lmdb data')
print(
'The first line is the path to image and the second line is the image label'
)
for i in range(demo_number):
print('image: %s\nlabel: %s\n' % (image_path_list[i], label_list[i]))
if __name__ == '__main__':
parser = argparse.ArgumentParser()
# parser.add_argument('--out', type = str, required = True, help = 'lmdb data output path')
parser.add_argument(
'--json_path',
type=str,
default='E:\\zj\\dataset\\icdar2015 (2)\\detection\\test.json',
help='path to gt json')
parser.add_argument('--save_floder',
type=str,
default=r'E:\zj\dataset\icdar2015 (2)',
help='path to save lmdb')
args = parser.parse_args()
data_dict = load_gt(args.json_path)
out_lmdb = os.path.join(args.save_floder, 'train')
createDataset(out_lmdb, data_dict, map_size=79951162)