[Bug] Unknown layout when running simple 3d inference models

[Lee4396]

Prerequisite

• [X] I have searched Issues and Discussions but cannot get the expected help.
• [X] The bug has not been fixed in the latest version(https://github.com/open-mmlab/mmpose).

Environment

Linux with Python3.10

Reproduces the problem - code sample

after installing the library and successfully inferenced the 2d models, I and getting an Unknown Layout error when trying to run demo/body3d_pose_lifter_demo.py

Reproduces the problem - command or script

python demo/body3d_pose_lifter_demo.py
demo/mmdetection_cfg/rtmdet_m_640-8xb32_coco-person.py
https://download.openmmlab.com/mmpose/v1/projects/rtmpose/rtmdet_m_8xb32-100e_coco-obj365-person-235e8209.pth
configs/body_2d_keypoint/rtmpose/body8/rtmpose-m_8xb256-420e_body8-256x192.py
https://download.openmmlab.com/mmpose/v1/projects/rtmposev1/rtmpose-m_simcc-body7_pt-body7_420e-256x192-e48f03d0_20230504.pth
configs/body_3d_keypoint/video_pose_lift/h36m/video-pose-lift_tcn-243frm-supv-cpn-ft_8xb128-200e_h36m.py
https://download.openmmlab.com/mmpose/body3d/videopose/videopose_h36m_243frames_fullconv_supervised_cpn_ft-88f5abbb_20210527.pth
--input https://user-images.githubusercontent.com/87690686/164970135-b14e424c-765a-4180-9bc8-fa8d6abc5510.mp4
--output-root vis_results
--save-predictions

Reproduces the problem - error message

Loads checkpoint by http backend from path: https://download.openmmlab.com/mmpose/v1/projects/rtmpose/rtmdet_m_8xb32-100e_coco-obj365-person-235e8209.pth Downloading: "https://download.openmmlab.com/mmpose/v1/projects/rtmpose/rtmdet_m_8xb32-100e_coco-obj365-person-235e8209.pth" to /home/ec2-user/.cache/torch/hub/checkpoints/rtmdet_m_8xb32-100e_coco-obj365-person-235e8209.pth 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████| 94.4M/94.4M [00:06<00:00, 16.1MB/s] Loads checkpoint by http backend from path: https://download.openmmlab.com/mmpose/v1/projects/rtmposev1/rtmpose-m_simcc-body7_pt-body7_420e-256x192-e48f03d0_20230504.pth Downloading: "https://download.openmmlab.com/mmpose/v1/projects/rtmposev1/rtmpose-m_simcc-body7_pt-body7_420e-256x192-e48f03d0_20230504.pth" to /home/ec2-user/.cache/torch/hub/checkpoints/rtmpose-m_simcc-body7_pt-body7_420e-256x192-e48f03d0_20230504.pth 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████| 52.0M/52.0M [00:03<00:00, 15.5MB/s] Loads checkpoint by http backend from path: https://download.openmmlab.com/mmpose/body3d/videopose/videopose_h36m_243frames_fullconv_supervised_cpn_ft-88f5abbb_20210527.pth Downloading: "https://download.openmmlab.com/mmpose/body3d/videopose/videopose_h36m_243frames_fullconv_supervised_cpn_ft-88f5abbb_20210527.pth" to /home/ec2-user/.cache/torch/hub/checkpoints/videopose_h36m_243frames_fullconv_supervised_cpn_ft-88f5abbb_20210527.pth 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████| 64.8M/64.8M [00:04<00:00, 15.6MB/s] /opt/conda/lib/python3.10/site-packages/torch/functional.py:507: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:3549.) return VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] Traceback (most recent call last): File "/home/ec2-user/mmpose/demo/body3d_pose_lifter_demo.py", line 553, in main() File "/home/ec2-user/mmpose/demo/body3d_pose_lifter_demo.py", line 488, in main next_id) = process_one_image( File "/home/ec2-user/mmpose/demo/body3d_pose_lifter_demo.py", line 213, in process_one_image det_result = inference_detector(detector, frame) File "/opt/conda/lib/python3.10/site-packages/mmdet/apis/inference.py", line 189, in inference_detector results = model.test_step(data)[0] File "/opt/conda/lib/python3.10/site-packages/mmengine/model/base_model/base_model.py", line 145, in test_step return self._run_forward(data, mode='predict') # type: ignore File "/opt/conda/lib/python3.10/site-packages/mmengine/model/base_model/base_model.py", line 361, in _run_forward results = self(**data, mode=mode) File "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1520, in _call_impl return forward_call(*args, **kwargs) File "/opt/conda/lib/python3.10/site-packages/mmdet/models/detectors/base.py", line 94, in forward return self.predict(inputs, data_samples) File "/opt/conda/lib/python3.10/site-packages/mmdet/models/detectors/single_stage.py", line 110, in predict results_list = self.bbox_head.predict( File "/opt/conda/lib/python3.10/site-packages/mmdet/models/dense_heads/base_dense_head.py", line 197, in predict predictions = self.predict_by_feat( File "/opt/conda/lib/python3.10/site-packages/mmdet/models/dense_heads/base_dense_head.py", line 279, in predict_by_feat results = self._predict_by_feat_single( File "/opt/conda/lib/python3.10/site-packages/mmdet/models/dense_heads/base_dense_head.py", line 423, in _predict_by_feat_single return self._bbox_post_process( File "/opt/conda/lib/python3.10/site-packages/mmdet/models/dense_heads/base_dense_head.py", line 485, in bbox_post_process det_bboxes, keep_idxs = batched_nms(bboxes, results.scores, File "/opt/conda/lib/python3.10/site-packages/mmcv/ops/nms.py", line 303, in batched_nms dets, keep = nms_op(boxes_for_nms, scores, **nms_cfg) File "/opt/conda/lib/python3.10/site-packages/mmengine/utils/misc.py", line 395, in new_func output = old_func(*args, **kwargs) File "/opt/conda/lib/python3.10/site-packages/mmcv/ops/nms.py", line 127, in nms inds = NMSop.apply(boxes, scores, iou_threshold, offset, score_threshold, File "/opt/conda/lib/python3.10/site-packages/torch/autograd/function.py", line 553, in apply return super().apply(*args, **kwargs) # type: ignore[misc] File "/opt/conda/lib/python3.10/site-packages/mmcv/ops/nms.py", line 27, in forward inds = ext_module.nms( RuntimeError: Unknown layout

Additional information

seems the older version of the code works

[Ben-Louis]

Could you please share the package details displayed by running pip list | grep mm? This could help identify any version discrepancies.

[Lee4396]

Could you please share the package details displayed by running pip list | grep mm? This could help identify any version discrepancies.

Hi,

Here it is

[Ben-Louis]

Based on the error message, it seems that there is an incompatibility between the pre-compiled package and your device. To fix the issue, try reinstalling mmcv from source using the command pip install git+https://github.com/open-mmlab/mmcv.git.

[Lee4396]

Based on the error message, it seems that there is an incompatibility between the pre-compiled package and your device. To fix the issue, try reinstalling mmcv from source using the command pip install git+https://github.com/open-mmlab/mmcv.git.

Yeah, I have tried this command and it gives the same error. It seems the command just installed the same version of mmcv.

[BenjiKCF]

Same issue