Closed cjyiiiing closed 2 years ago
Please use dist_train.sh
to train models.
Please refer to here to train VID methods.
I use this command now:
bash ./tools/dist_train.sh ./configs/vid/temporal_roi_align/mydata_selsa_troialign_faster_rcnn_r50_dc5_7e_imagenetvid.py 2 --work-dir ./mydata_selsa_troialign_faster_rcnn_r50_dc5_7e_imagenetvid/
but still have the same error:
Traceback (most recent call last): File "./tools/train.py", line 179, in
main() File "./tools/train.py", line 175, in main meta=meta) File "/home/fwq2/lab/cjy/VOD/mmtracking/mmtrack/apis/train.py", line 93, in train_model seed=cfg.seed) for ds in dataset File "/home/fwq2/lab/cjy/VOD/mmtracking/mmtrack/apis/train.py", line 93, in seed=cfg.seed) for ds in dataset File "/home/fwq2/lab/cjy/VOD/mmtracking/mmtrack/datasets/builder.py", line 49, in build_dataloader world_size, rank) File "/home/fwq2/.conda/envs/open-mmlab/lib/python3.7/site-packages/mmdet/datasets/samplers/group_sampler.py", line 90, in init assert hasattr(self.dataset, 'flag') AssertionError Traceback (most recent call last): File "./tools/train.py", line 179, in main() File "./tools/train.py", line 175, in main meta=meta) File "/home/fwq2/lab/cjy/VOD/mmtracking/mmtrack/apis/train.py", line 93, in train_model seed=cfg.seed) for ds in dataset File "/home/fwq2/lab/cjy/VOD/mmtracking/mmtrack/apis/train.py", line 93, in seed=cfg.seed) for ds in dataset File "/home/fwq2/lab/cjy/VOD/mmtracking/mmtrack/datasets/builder.py", line 49, in build_dataloader world_size, rank) File "/home/fwq2/.conda/envs/open-mmlab/lib/python3.7/site-packages/mmdet/datasets/samplers/group_sampler.py", line 90, in init assert hasattr(self.dataset, 'flag') AssertionError Traceback (most recent call last): File "/home/fwq2/.conda/envs/open-mmlab/lib/python3.7/runpy.py", line 193, in _run_module_as_main "main", mod_spec) File "/home/fwq2/.conda/envs/open-mmlab/lib/python3.7/runpy.py", line 85, in _run_code exec(code, run_globals) File "/home/fwq2/.conda/envs/open-mmlab/lib/python3.7/site-packages/torch/distributed/launch.py", line 261, in main() File "/home/fwq2/.conda/envs/open-mmlab/lib/python3.7/site-packages/torch/distributed/launch.py", line 257, in main cmd=cmd) subprocess.CalledProcessError: Command '['/home/fwq2/.conda/envs/open-mmlab/bin/python', '-u', './tools/train.py', '--local_rank=1', './configs/vid/temporal_roi_align/mydata_selsa_troialign_faster_rcnn_r50_dc5_7e_imagenetvid.py', '--launcher', 'pytorch', '--work-dir', './mydata_selsa_troialign_faster_rcnn_r50_dc5_7e_imagenetvid/']' returned non-zero exit status 1.
Please set test_mode=False
in the training dataset of your config, since test_mode=True
means the dataset runing in testing mode.
Hi, I am facing the same error. And, I have tried the above given solutions but still no luck.
bash ./tools/dist_train.sh /configs/vid/temporal_roi_align/selsa_troialign_faster_rcnn_r50_dc5_7e_imagenetvid.py 2
Traceback (most recent call last):
File "./tools/train.py", line 251, in
I used the command
python tools/train.py ./configs/vid/temporal_roi_align/mydata_selsa_troialign_faster_rcnn_r50_dc5_7e_imagenetvid.py --device 1
to train Temporal ROI Align on my custom dataset, But I meet one error. The output isI have searched related issues but still cannot fix this error.
mydata_selsa_troialign_faster_rcnn_r50_dc5_7e_imagenetvid.py:
my environment: