RuntimeError

[gubei1998]

Error is as following,I do not know how to solve it
File "./tools/train.py", line 168, in
main()
File "./tools/train.py", line 157, in main
train_detector(
File "/opt/zcy/anaconda/envs/ctp/CenterPoint/det3d/torchie/apis/train.py", line 326, in train_detector
trainer.run(data_loaders, cfg.workflow, cfg.total_epochs, local_rank=cfg.local_rank)
File "/opt/zcy/anaconda/envs/ctp/CenterPoint/det3d/torchie/trainer/trainer.py", line 542, in run
epoch_runner(data_loaders[i], self.epoch, **kwargs)
File "/opt/zcy/anaconda/envs/ctp/CenterPoint/det3d/torchie/trainer/trainer.py", line 417, in train
self.call_hook("after_train_iter")
File "/opt/zcy/anaconda/envs/ctp/CenterPoint/det3d/torchie/trainer/trainer.py", line 330, in call_hook
getattr(hook, fn_name)(self)
File "/opt/zcy/anaconda/envs/ctp/CenterPoint/det3d/torchie/trainer/hooks/optimizer.py", line 18, in after_train_iter
trainer.outputs["loss"].backward()
File "/opt/zcy/anaconda/envs/ctp/lib/python3.8/site-packages/torch/_tensor.py", line 396, in backward
torch.autograd.backward(self, gradient, retain_graph, create_graph, inputs=inputs)
File "/opt/zcy/anaconda/envs/ctp/lib/python3.8/site-packages/torch/autograd/init.py", line 173, in backward
Variable._execution_engine.run_backward( # Calls into the C++ engine to run the backward pass
File "/opt/zcy/anaconda/envs/ctp/lib/python3.8/site-packages/torch/autograd/function.py", line 253, in apply
return user_fn(self, *args)
File "/opt/zcy/anaconda/envs/ctp/lib/python3.8/site-packages/torch/autograd/function.py", line 399, in wrapper
outputs = fn(ctx, *args)
File "/opt/zcy/anaconda/envs/ctp/CenterPoint/det3d/ops/dcn/deform_conv.py", line 87, in backward
deform_conv_cuda.deform_conv_backward_parameters_cuda(
RuntimeError: view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous subspaces). Use .reshape(...) instead.

[tianweiy]

#237 (comment)

hi, please use a config without dcn e.g. https://github.com/tianweiy/CenterPoint/blob/master/configs/nusc/voxelnet/nusc_centerpoint_voxelnet_0075voxel_fix_bn_z.py

their results are also competitive #249

[gubei1998]

#237 (comment)

hi, please use a config without dcn e.g. https://github.com/tianweiy/CenterPoint/blob/master/configs/nusc/voxelnet/nusc_centerpoint_voxelnet_0075voxel_fix_bn_z.py

their results are also competitive #249

Thank you for your answer very much