mmrotate
mmrotate copied to clipboard
[Bug] Error while loading HRSC dataset
Prerequisite
- [X] I have searched Issues and Discussions but cannot get the expected help.
- [X] I have read the FAQ documentation but cannot get the expected help.
- [X] The bug has not been fixed in the latest version (master) or latest version (1.x).
Task
I'm using the official example scripts/configs for the officially supported tasks/models/datasets.
Branch
master branch https://github.com/open-mmlab/mmrotate
Environment
mmcv-full 1.7.1 mmdet 2.28.2
Reproduces the problem - code sample
mmrotate/datasets/hrsc.py
row98
xml_path = osp.join(self.img_prefix, self.ann_subdir, f'{img_id}.xml')
Connecting img_prefix and ann_subdir resulted in a path not being found
Reproduces the problem - command or script
python tools/train.py configs/s2anet/s2anet_r50_fpn_3x_hrsc_le135.py --gpus 1 --work-dir work_dirs
Reproduces the problem - error message
FileNotFoundError: [Errno 2] No such file or directory: 'data/hrsc/FullDataSet/AllImages/data/hrsc/FullDataSet/Annotations/100000001.xml'
Additional information
mmrotate/datasets/hrsc.py
row98
xml_path = osp.join(self.img_prefix, self.ann_subdir, f'{img_id}.xml')
Connecting img_prefix and ann_subdir resulted in a path not being found
你看下 ‘data/hrsc/FullDataSet/AllImages/data/hrsc/FullDataSet/Annotations/100000001.xml’ 是否有这个文件,然后根据错误修改配置文件就可以了。
请问有解决方案了吗
我也出现这样的问题,感觉像把路径img_prefix和ann_subdir加到了一起,请问有解决方案吗
我删去了一行之后显示ValueError: need at least one array to concatenate