131 lines
4.3 KiB
Python
131 lines
4.3 KiB
Python
"""
|
|
数据集下载和准备脚本
|
|
"""
|
|
import os
|
|
import argparse
|
|
import shutil
|
|
from pathlib import Path
|
|
|
|
|
|
def create_dummy_dataset(output_dir, num_classes=10, images_per_class=100):
|
|
"""
|
|
创建示例数据集结构
|
|
|
|
Args:
|
|
output_dir: 输出目录
|
|
num_classes: 类别数量
|
|
images_per_class: 每个类别的图像数量
|
|
"""
|
|
print(f"创建数据集结构: {output_dir}")
|
|
|
|
# 创建训练集和验证集
|
|
for split in ['train', 'val']:
|
|
split_dir = os.path.join(output_dir, split)
|
|
os.makedirs(split_dir, exist_ok=True)
|
|
|
|
# 创建类别目录
|
|
for class_id in range(num_classes):
|
|
class_dir = os.path.join(split_dir, f'class_{class_id}')
|
|
os.makedirs(class_dir, exist_ok=True)
|
|
|
|
# 创建占位符文件
|
|
readme_path = os.path.join(class_dir, 'README.txt')
|
|
with open(readme_path, 'w', encoding='utf-8') as f:
|
|
f.write(f'类别 {class_id}: {class_id}个光瓣\n')
|
|
f.write(f'请在此目录放置 {images_per_class} 张图像\n')
|
|
f.write('支持的格式: .jpg, .jpeg, .png\n')
|
|
|
|
print("数据集结构创建完成!")
|
|
print("\n目录结构:")
|
|
print(f"{output_dir}/")
|
|
print(" ├── train/")
|
|
print(" │ ├── class_0/ (0个光瓣)")
|
|
print(" │ ├── class_1/ (1个光瓣)")
|
|
print(" │ └── ...")
|
|
print(" └── val/")
|
|
print(" ├── class_0/")
|
|
print(" └── ...")
|
|
print("\n请将图像放入对应的类别目录中")
|
|
|
|
|
|
def split_dataset(source_dir, output_dir, train_ratio=0.8):
|
|
"""
|
|
将数据集分割为训练集和验证集
|
|
|
|
Args:
|
|
source_dir: 源数据目录
|
|
output_dir: 输出目录
|
|
train_ratio: 训练集比例
|
|
"""
|
|
import random
|
|
|
|
print(f"分割数据集: {source_dir} -> {output_dir}")
|
|
|
|
# 创建输出目录
|
|
train_dir = os.path.join(output_dir, 'train')
|
|
val_dir = os.path.join(output_dir, 'val')
|
|
os.makedirs(train_dir, exist_ok=True)
|
|
os.makedirs(val_dir, exist_ok=True)
|
|
|
|
# 遍历类别
|
|
for class_name in os.listdir(source_dir):
|
|
class_path = os.path.join(source_dir, class_name)
|
|
if not os.path.isdir(class_path):
|
|
continue
|
|
|
|
# 获取所有图像
|
|
images = [f for f in os.listdir(class_path)
|
|
if f.lower().endswith(('.png', '.jpg', '.jpeg'))]
|
|
|
|
# 随机打乱
|
|
random.shuffle(images)
|
|
|
|
# 分割
|
|
split_idx = int(len(images) * train_ratio)
|
|
train_images = images[:split_idx]
|
|
val_images = images[split_idx:]
|
|
|
|
# 创建类别目录
|
|
train_class_dir = os.path.join(train_dir, class_name)
|
|
val_class_dir = os.path.join(val_dir, class_name)
|
|
os.makedirs(train_class_dir, exist_ok=True)
|
|
os.makedirs(val_class_dir, exist_ok=True)
|
|
|
|
# 复制文件
|
|
for img in train_images:
|
|
src = os.path.join(class_path, img)
|
|
dst = os.path.join(train_class_dir, img)
|
|
shutil.copy2(src, dst)
|
|
|
|
for img in val_images:
|
|
src = os.path.join(class_path, img)
|
|
dst = os.path.join(val_class_dir, img)
|
|
shutil.copy2(src, dst)
|
|
|
|
print(f"{class_name}: {len(train_images)} 训练, {len(val_images)} 验证")
|
|
|
|
print("数据集分割完成!")
|
|
|
|
|
|
if __name__ == '__main__':
|
|
parser = argparse.ArgumentParser(description='数据集准备工具')
|
|
parser.add_argument('--mode', type=str, choices=['create', 'split'],
|
|
required=True, help='操作模式')
|
|
parser.add_argument('--output', type=str, required=True,
|
|
help='输出目录')
|
|
parser.add_argument('--source', type=str, default=None,
|
|
help='源数据目录(split模式)')
|
|
parser.add_argument('--num_classes', type=int, default=10,
|
|
help='类别数量(create模式)')
|
|
parser.add_argument('--train_ratio', type=float, default=0.8,
|
|
help='训练集比例(split模式)')
|
|
|
|
args = parser.parse_args()
|
|
|
|
if args.mode == 'create':
|
|
create_dummy_dataset(args.output, args.num_classes)
|
|
elif args.mode == 'split':
|
|
if args.source is None:
|
|
print("错误: split模式需要指定--source参数")
|
|
else:
|
|
split_dataset(args.source, args.output, args.train_ratio) |