hi @csuhan and tnx very much for answering
i want to train ReDet_re50_refpn_3x_hrsc2016
my env is colab tesla t4 and use pytorch 1.1
in training i got this error:
File "tools/train.py", line 95, in
main()
File "tools/train.py", line 91, in main
logger=logger)
File "/content/ReDet/mmdet/apis/train.py", line 61, in train_detector
_non_dist_train(model, dataset, cfg, validate=validate)
File "/content/ReDet/mmdet/apis/train.py", line 197, in _non_dist_train
runner.run(data_loaders, cfg.workflow, cfg.total_epochs)
File "/usr/local/lib/python3.7/dist-packages/mmcv-0.2.13-py3.7-linux-x86_64.egg/mmcv/runner/runner.py", line 358, in run
epoch_runner(data_loaders[i], **kwargs)
File "/usr/local/lib/python3.7/dist-packages/mmcv-0.2.13-py3.7-linux-x86_64.egg/mmcv/runner/runner.py", line 271, in train
self.call_hook('after_train_iter')
File "/usr/local/lib/python3.7/dist-packages/mmcv-0.2.13-py3.7-linux-x86_64.egg/mmcv/runner/runner.py", line 229, in call_hook
getattr(hook, fn_name)(self)
File "/usr/local/lib/python3.7/dist-packages/mmcv-0.2.13-py3.7-linux-x86_64.egg/mmcv/runner/hooks/optimizer.py", line 17, in after_train_iter
runner.outputs['loss'].backward()
File "/usr/local/lib/python3.7/dist-packages/torch/tensor.py", line 107, in backward
torch.autograd.backward(self, gradient, retain_graph, create_graph)
File "/usr/local/lib/python3.7/dist-packages/torch/autograd/init.py", line 93, in backward
allow_unreachable=True) # allow_unreachable flag
File "/usr/local/lib/python3.7/dist-packages/torch/autograd/function.py", line 77, in apply
return self._forward_cls.backward(self, *args)
File "/content/ReDet/mmdet/ops/riroi_align/functions/riroi_align.py", line 58, in backward
grad_input)
RuntimeError: cuda runtime error (701) : unrecognized error code at src/riroi_align_kernel.cu:389
i red issues/4 but i dont understand what should i do???
Maybe the mismatch between your pytorch
and cudatoolkit
. Please check it.
Maybe the mismatch between your pytorch
and cudatoolkit
. Please check it.
it can train roi transform and frCNN_OBB in HRSC2016 and DOTA
it happen when i want train just ReDet configs ):