Visualization error

[hsingyu-chou]

I try to visualize the results but it occur the error as below. How could I solve with this issue?

My command :

!torchpack dist-run -np 1 python tools/visualize.py configs/nuscenes/det/transfusion/secfpn/camera+lidar/swint_v0p075/convfuser.yaml --mode pred --checkpoint pretrained/bevfusion-det.pth --bbox-score 0.5 --out-dir vis_results

The error :

Traceback (most recent call last):
  File "/content/bevfusion/tools/visualize.py", line 166, in <module>
    main()
  File "/content/bevfusion/tools/visualize.py", line 88, in main
    outputs = model(**data)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/parallel/distributed.py", line 1156, in forward
    output = self._run_ddp_forward(*inputs, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/mmcv/parallel/distributed.py", line 165, in _run_ddp_forward
    return module_to_run(*inputs[0], **kwargs[0])  # type: ignore
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/mmcv/runner/fp16_utils.py", line 119, in new_func
    return old_func(*args, **kwargs)
  File "/content/bevfusion/mmdet3d/models/fusion_models/bevfusion.py", line 253, in forward
    outputs = self.forward_single(
  File "/usr/local/lib/python3.10/dist-packages/mmcv/runner/fp16_utils.py", line 119, in new_func
    return old_func(*args, **kwargs)
  File "/content/bevfusion/mmdet3d/models/fusion_models/bevfusion.py", line 301, in forward_single
    feature = self.extract_camera_features(
  File "/content/bevfusion/mmdet3d/models/fusion_models/bevfusion.py", line 133, in extract_camera_features
    x = self.encoders["camera"]["vtransform"](
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "/content/bevfusion/mmdet3d/models/vtransforms/depth_lss.py", line 100, in forward
    x = super().forward(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/mmcv/runner/fp16_utils.py", line 208, in new_func
    return old_func(*args, **kwargs)
  File "/content/bevfusion/mmdet3d/models/vtransforms/base.py", line 350, in forward
    x = self.get_cam_feats(img, depth, mats_dict)
  File "/usr/local/lib/python3.10/dist-packages/mmcv/runner/fp16_utils.py", line 208, in new_func
    return old_func(*args, **kwargs)
TypeError: DepthLSSTransform.get_cam_feats() takes 3 positional arguments but 4 were given

[NuanBaobao]

I am also experiencing this error, how did you fix it?

[kongwah]

Hello, I encountered a similar issue. Any solution? Please see the error output below. Thanks

File "tools/visualize.py", line 168, in main() File "tools/visualize.py", line 90, in main outputs = model(**data) File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl return forward_call(*input, **kwargs) File "/opt/conda/lib/python3.8/site-packages/torch/nn/parallel/distributed.py", line 886, in forward output = self.module(*inputs[0], **kwargs[0]) File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl return forward_call(*input, **kwargs) File "/opt/conda/lib/python3.8/site-packages/mmcv/runner/fp16_utils.py", line 98, in new_func return old_func(*args, **kwargs) File "/home/bevfusion/mmdet3d/models/fusion_models/bevfusion.py", line 253, in forward outputs = self.forward_single( File "/opt/conda/lib/python3.8/site-packages/mmcv/runner/fp16_utils.py", line 98, in new_func return old_func(*args, **kwargs) File "/home/bevfusion/mmdet3d/models/fusion_models/bevfusion.py", line 301, in forward_single feature = self.extract_camera_features( File "/home/bevfusion/mmdet3d/models/fusion_models/bevfusion.py", line 133, in extract_camera_features x = self.encoders["camera"]["vtransform"]( File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl return forward_call(*input, **kwargs) File "/home/bevfusion/mmdet3d/models/vtransforms/depth_lss.py", line 100, in forward x = super().forward(*args, **kwargs) File "/opt/conda/lib/python3.8/site-packages/mmcv/runner/fp16_utils.py", line 186, in new_func return old_func(*args, **kwargs) File "/home/bevfusion/mmdet3d/models/vtransforms/base.py", line 352, in forward x = self.get_cam_feats(img, depth, mats_dict) File "/opt/conda/lib/python3.8/site-packages/mmcv/runner/fp16_utils.py", line 186, in new_func return old_func(*args, **kwargs) TypeError: get_cam_feats() takes 3 positional arguments but 4 were given

[TimDing-aoi]

I got the same error.

[kongwah]

I resolved it by the following: -- compare the code between test.py and visualize.py -- since test.py works, check what is in test.py that is missing in visualize.py -- one such missing code snippet relates to wrap_fp16_model -- modify visualize.py accordingly to be the same as test.py

[bharathsivaram10]

This is the same as #532, this should help: solution