RuntimeError: There were no tensor arguments to this function

[YJYJLee]

Hello, I downloaded pretrained model for ScanNetV2 from https://drive.google.com/file/d/1XUNRfred9QAEUY__VdmSgZxGQ7peG5ms/view?usp=sharing in README and ran inference.

However, I got the following error.

Traceback (most recent call last):
File "./tools/test.py", line 146, in
main()
File "./tools/test.py", line 102, in main
result = model(batch)
File "/home2/yejin/anaconda3/envs/softgroup/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
File "/home2/yejin/anaconda3/envs/softgroup/lib/python3.7/site-packages/torch/nn/parallel/distributed.py", line 705, in forward
output = self.module(*inputs[0], **kwargs[0])
File "/home2/yejin/anaconda3/envs/softgroup/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
File "/home2/yejin/PointCloud_models/SoftGroup/softgroup/model/softgroup.py", line 99, in forward
return self.forward_test(**batch)
File "/home2/yejin/PointCloud_models/SoftGroup/softgroup/util/utils.py", line 171, in wrapper
return func(*new_args, **new_kwargs)
File "/home2/yejin/PointCloud_models/SoftGroup/softgroup/model/softgroup.py", line 246, in forward_test
self.grouping_cfg)
File "/home2/yejin/PointCloud_models/SoftGroup/softgroup/util/fp16.py", line 58, in new_func
output = old_func(*new_args, **new_kwargs)
File "/home2/yejin/PointCloud_models/SoftGroup/softgroup/model/softgroup.py", line 344, in forward_grouping
proposals_idx = torch.cat(proposals_idx_list, dim=0)
RuntimeError: There were no tensor arguments to this function (e.g., you passed an empty list of Tensors), but no fallback function is registered for schema aten::_cat. This usually means that this function requires a non-empty list of Tensors. Available functions are [CPU, CUDA, QuantizedCPU, BackendSelect, Named, AutogradOther, AutogradCPU, AutogradCUDA, AutogradXLA, AutogradNestedTensor, UNKNOWN_TENSOR_TYPE_ID, AutogradPrivateUse1, AutogradPrivateUse2, AutogradPrivateUse3, Tracer, Autocast, Batched, VmapMode].

My GPU is A100, and using torch 1.8.1.

Also, I modified dist_test.sh line 7 to OMP_NUM_THREADS=1 python -m torch.distributed.launch --use_env --nproc_per_node=$GPUS --master_port=$PORT $(dirname "$0")/test.py $CONFIG $CHECK_POINT --dist ${@:4} since torchrun is supported from torch 1.11.0.

[thangvubk]

The error shows that grouping doesnot return any valid proposal. Can you set semantic_only to True and tell the sematic mIoU, Acc and offset MAE.

[YJYJLee]

Thanks for the quick reply!

I was trying to run as you said, however I ran into another error

2022-04-17 14:48:47,455 - INFO - Load state dict from /arc-share/pc_yejin/checkpoints/SoftGroup/softgroup_scannet_spconv2.pth
2022-04-17 14:48:48,616 - INFO - unexpected key in source state_dict: tiny_unet.blocks.block0.conv_branch.0.weight, tiny_unet.blocks.block0.conv_branch.0.bias, tiny_unet.blocks.block0.conv_branch.0.running_mean, tiny_unet.blocks.block0.conv_branch.0.running_var, tiny_unet.blocks.block0.conv_branch.0.num_batches_tracked, tiny_unet.blocks.block0.conv_branch.2.weight, tiny_unet.blocks.block0.conv_branch.3.weight, tiny_unet.blocks.block0.conv_branch.3.bias, tiny_unet.blocks.block0.conv_branch.3.running_mean, tiny_unet.blocks.block0.conv_branch.3.running_var, tiny_unet.blocks.block0.conv_branch.3.num_batches_tracked, tiny_unet.blocks.block0.conv_branch.5.weight, tiny_unet.blocks.block1.conv_branch.0.weight, tiny_unet.blocks.block1.conv_branch.0.bias, tiny_unet.blocks.block1.conv_branch.0.running_mean, tiny_unet.blocks.block1.conv_branch.0.running_var, tiny_unet.blocks.block1.conv_branch.0.num_batches_tracked, tiny_unet.blocks.block1.conv_branch.2.weight, tiny_unet.blocks.block1.conv_branch.3.weight, tiny_unet.blocks.block1.conv_branch.3.bias, tiny_unet.blocks.block1.conv_branch.3.running_mean, tiny_unet.blocks.block1.conv_branch.3.running_var, tiny_unet.blocks.block1.conv_branch.3.num_batches_tracked, tiny_unet.blocks.block1.conv_branch.5.weight, tiny_unet.conv.0.weight, tiny_unet.conv.0.bias, tiny_unet.conv.0.running_mean, tiny_unet.conv.0.running_var, tiny_unet.conv.0.num_batches_tracked, tiny_unet.conv.2.weight, tiny_unet.u.blocks.block0.conv_branch.0.weight, tiny_unet.u.blocks.block0.conv_branch.0.bias, tiny_unet.u.blocks.block0.conv_branch.0.running_mean, tiny_unet.u.blocks.block0.conv_branch.0.running_var, tiny_unet.u.blocks.block0.conv_branch.0.num_batches_tracked, tiny_unet.u.blocks.block0.conv_branch.2.weight, tiny_unet.u.blocks.block0.conv_branch.3.weight, tiny_unet.u.blocks.block0.conv_branch.3.bias, tiny_unet.u.blocks.block0.conv_branch.3.running_mean, tiny_unet.u.blocks.block0.conv_branch.3.running_var, tiny_unet.u.blocks.block0.conv_branch.3.num_batches_tracked, tiny_unet.u.blocks.block0.conv_branch.5.weight, tiny_unet.u.blocks.block1.conv_branch.0.weight, tiny_unet.u.blocks.block1.conv_branch.0.bias, tiny_unet.u.blocks.block1.conv_branch.0.running_mean, tiny_unet.u.blocks.block1.conv_branch.0.running_var, tiny_unet.u.blocks.block1.conv_branch.0.num_batches_tracked, tiny_unet.u.blocks.block1.conv_branch.2.weight, tiny_unet.u.blocks.block1.conv_branch.3.weight, tiny_unet.u.blocks.block1.conv_branch.3.bias, tiny_unet.u.blocks.block1.conv_branch.3.running_mean, tiny_unet.u.blocks.block1.conv_branch.3.running_var, tiny_unet.u.blocks.block1.conv_branch.3.num_batches_tracked, tiny_unet.u.blocks.block1.conv_branch.5.weight, tiny_unet.deconv.0.weight, tiny_unet.deconv.0.bias, tiny_unet.deconv.0.running_mean, tiny_unet.deconv.0.running_var, tiny_unet.deconv.0.num_batches_tracked, tiny_unet.deconv.2.weight, tiny_unet.blocks_tail.block0.i_branch.0.weight, tiny_unet.blocks_tail.block0.conv_branch.0.weight, tiny_unet.blocks_tail.block0.conv_branch.0.bias, tiny_unet.blocks_tail.block0.conv_branch.0.running_mean, tiny_unet.blocks_tail.block0.conv_branch.0.running_var, tiny_unet.blocks_tail.block0.conv_branch.0.num_batches_tracked, tiny_unet.blocks_tail.block0.conv_branch.2.weight, tiny_unet.blocks_tail.block0.conv_branch.3.weight, tiny_unet.blocks_tail.block0.conv_branch.3.bias, tiny_unet.blocks_tail.block0.conv_branch.3.running_mean, tiny_unet.blocks_tail.block0.conv_branch.3.running_var, tiny_unet.blocks_tail.block0.conv_branch.3.num_batches_tracked, tiny_unet.blocks_tail.block0.conv_branch.5.weight, tiny_unet.blocks_tail.block1.conv_branch.0.weight, tiny_unet.blocks_tail.block1.conv_branch.0.bias, tiny_unet.blocks_tail.block1.conv_branch.0.running_mean, tiny_unet.blocks_tail.block1.conv_branch.0.running_var, tiny_unet.blocks_tail.block1.conv_branch.0.num_batches_tracked, tiny_unet.blocks_tail.block1.conv_branch.2.weight, tiny_unet.blocks_tail.block1.conv_branch.3.weight, tiny_unet.blocks_tail.block1.conv_branch.3.bias, tiny_unet.blocks_tail.block1.conv_branch.3.running_mean, tiny_unet.blocks_tail.block1.conv_branch.3.running_var, tiny_unet.blocks_tail.block1.conv_branch.3.num_batches_tracked, tiny_unet.blocks_tail.block1.conv_branch.5.weight, tiny_unet_outputlayer.0.weight, tiny_unet_outputlayer.0.bias, tiny_unet_outputlayer.0.running_mean, tiny_unet_outputlayer.0.running_var, tiny_unet_outputlayer.0.num_batches_tracked, iou_score_linear.weight, iou_score_linear.bias, cls_linear.weight, cls_linear.bias, mask_linear.0.weight, mask_linear.0.bias, mask_linear.2.weight, mask_linear.2.bias
2022-04-17 14:48:48,620 - INFO - Load test dataset: 312 scans
0%| | 0/312 [00:00<?, ?it/s]None
Traceback (most recent call last):
File "./tools/test.py", line 146, in
main()
File "./tools/test.py", line 102, in main
result = model(batch)
TypeError: 'NoneType' object is not callable
0%|

It seems like the checkpoint does not match the model..
I found out after doing model.eval() in test.py:98, the model somehow becomes None.
Any solution for this?

[thangvubk]

The checkpoint mismatch is expected because we truncate the instance segmentation components. Which pytorch version are you using? Could you try to replace model = model.eval() by model.eval()

[YJYJLee]

Replacing model=model.eval() to model.eval() works well! Thanks

I'm sorry, I found out the cause of the error "RuntimeError: There were no tensor arguments to this function".
It was because of spconv. I found out that spconv v2 was somehow not built properly. I built it from the source and I might have done something wrong.
I installed spconv with pip (pip install spconv-cu111) and it works perfectly!

Sorry again, nice work!