I found the paper fascinating and am grateful for the amazing work.
I am in the process of testing HR-SegRefiner.
I have generated coarse masks using python scripts/gen_coarse_masks_hr.py and have proceeded with training using python tools/train.py configs/segrefiner/segrefiner_hr.py.
However, when I entered python tools/test.py configs/segrefiner/segrefiner_big.py checkpoints/segrefiner_hr_latest.pth --out_dir ./test_model_name for evaluation, the following problem occurred. Do I need to download the data and create a folder path?
(segrefiner) sj@sjpc:~/sj_ws/SegRefiner_main$ python tools/test.py configs/segrefiner/segrefiner_big.py checkpoints/segrefiner_hr_latest.pth --out_dir ./test_model_name
/home/sj/anaconda3/envs/segrefiner/lib/python3.8/site-packages/mmcv/__init__.py:20: UserWarning: On January 1, 2023, MMCV will release v2.0.0, in which it will remove components related to the training process and add a data transformation module. In addition, it will rename the package names mmcv to mmcv-lite and mmcv-full to mmcv. See https://github.com/open-mmlab/mmcv/blob/master/docs/en/compatibility.md for more details.
warnings.warn(
Traceback (most recent call last):
File "/home/sj/anaconda3/envs/segrefiner/lib/python3.8/site-packages/mmcv/utils/registry.py", line 69, in build_from_cfg
return obj_cls(**args)
File "/home/sj/sj_ws/SegRefiner_main/mmdet/datasets/big.py", line 41, in __init__
self.data_infos = self.load_datas(self.data_root)
File "/home/sj/sj_ws/SegRefiner_main/mmdet/datasets/big.py", line 55, in load_datas
all_files = os.listdir(data_root)
FileNotFoundError: [Errno 2] No such file or directory: 'data/big/coarse/deeplab'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "tools/test.py", line 237, in <module>
main()
File "tools/test.py", line 184, in main
dataset = build_dataset(cfg.data.test)
File "/home/sj/sj_ws/SegRefiner_main/mmdet/datasets/builder.py", line 82, in build_dataset
dataset = build_from_cfg(cfg, DATASETS, default_args)
File "/home/sj/anaconda3/envs/segrefiner/lib/python3.8/site-packages/mmcv/utils/registry.py", line 72, in build_from_cfg
raise type(e)(f'{obj_cls.__name__}: {e}')
FileNotFoundError: BigDataset: [Errno 2] No such file or directory: 'data/big/coarse/deeplab'
I found the paper fascinating and am grateful for the amazing work.
I am in the process of testing HR-SegRefiner. I have generated coarse masks using
python scripts/gen_coarse_masks_hr.py
and have proceeded with training usingpython tools/train.py configs/segrefiner/segrefiner_hr.py.
However, when I entered
python tools/test.py configs/segrefiner/segrefiner_big.py checkpoints/segrefiner_hr_latest.pth --out_dir ./test_model_name
for evaluation, the following problem occurred. Do I need to download the data and create a folder path?