目标检测数据集VOC打卡

打卡目标检测

1. 数据集准备
   “”“python
   create_data_lists
   “””
   from utils import create_data_lists

if name == ‘main’:
# voc07_path，voc12_path为我们训练测试所需要用到的数据集，output_folder为我们生成构建dataloader所需文件的路径
# 参数中涉及的路径以个人实际路径为准，建议将数据集放到dataset目录下，和教程保持一致
create_data_lists(voc07_path=’…/…/…/dataset/VOCdevkit/VOC2007’,
voc12_path=’…/…/…/dataset/VOCdevkit/VOC2012’,
output_folder=’…/…/…/dataset/VOCdevkit’)

2. 构建dataloader
   #train_dataset和train_loader的实例化
   train_dataset = PascalVOCDataset(data_folder,
   split=‘train’,
   keep_difficult=keep_difficult)
   train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=batch_size, shuffle=True,
   collate_fn=train_dataset.collate_fn, num_workers=workers,
   pin_memory=True) # note that we’re passing the collate function