Padel创建数据集列表

import json
import os

def create_data_list(data_root_path):
with open(data_root_path + "test.list", 'w') as f:
pass
with open(data_root_path + "train.list", 'w') as f:
pass
# 所有类别的信息
class_detail = []
# 获取所有类别
class_dirs = os.listdir(data_root_path)
# 类别标签
class_label = 0
# 获取总类别的名称
father_paths = data_root_path.split('/')
while True:
if father_paths[len(father_paths) - 1] == '':
del father_paths[len(father_paths) - 1]
else:
break
father_path = father_paths[len(father_paths) - 1]

all_class_images = 0
other_file = 0
# 读取每个类别
for class_dir in class_dirs:
if class_dir == 'test.list' or class_dir == "train.list" or class_dir == 'readme.json':
other_file += 1
continue
print('正在读取类别：%s' % class_dir)
# 每个类别的信息
class_detail_list = {}
test_sum = 0
trainer_sum = 0
# 统计每个类别有多少张图片
class_sum = 0
# 获取类别路径
path = data_root_path + "/" + class_dir
# 获取所有图片
img_paths = os.listdir(path)
for img_path in img_paths:
# 每张图片的路径
name_path = class_dir + '/' + img_path
# 如果不存在这个文件夹,就创建
if not os.path.exists(data_root_path):
os.makedirs(data_root_path)
# 每10张图片取一个做测试数据
if class_sum % 10 == 0:
test_sum += 1
with open(data_root_path + "test.list", 'a') as f:
f.write(name_path + "\t%d" % class_label + "\n")
else:
trainer_sum += 1
with open(data_root_path + "train.list", 'a') as f:
f.write(name_path + "\t%d" % class_label + "\n")
class_sum += 1
all_class_images += 1
# 说明的json文件的class_detail数据
class_detail_list['class_name'] = class_dir
class_detail_list['class_label'] = class_label
class_detail_list['class_test_images'] = test_sum
class_detail_list['class_trainer_images'] = trainer_sum
class_detail.append(class_detail_list)
class_label += 1
# 获取类别数量
all_class_sum = len(class_dirs) - other_file
# 说明的json文件信息
readjson = {}
readjson['all_class_name'] = father_path
readjson['all_class_sum'] = all_class_sum
readjson['all_class_images'] = all_class_images
readjson['class_detail'] = class_detail
jsons = json.dumps(readjson, sort_keys=True, indent=4, separators=(',', ': '))
with open(data_root_path + "readme.json", 'w') as f:
f.write(jsons)
print('图像列表已生成')