open-mmlab
pt->onnx ->engine 中报错，求解决
Checklist
- [ ] I have searched related issues but cannot get the expected help.
- [ ] 2. I have read the FAQ documentation but cannot get the expected help.
- [ ] 3. The bug has not been fixed in the latest version.
Describe the bug
python mmdeploy/tools/deploy.py mmdeploy/configs/mmdet/detection/detection_tensorrt_dynamic-320x320-1344x1344.py rtmdet_tiny_8xb32-300e_coco.py rtmdet_tiny_8xb32-300e_coco_20220902_112414-78e30dcc.pth mmdetection/demo/demo.jpg --work-dir weights --device cuda --dump-info 03/18 17:01:10 - mmengine - WARNING - Failed to search registry with scope "mmdet" in the "Codebases" registry tree. As a workaround, the current "Codebases" registry in "mmdeploy" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmdet" is a correct scope, or whether the registry is initialized. 03/18 17:01:10 - mmengine - WARNING - Failed to search registry with scope "mmdet" in the "mmdet_tasks" registry tree. As a workaround, the current "mmdet_tasks" registry in "mmdeploy" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmdet" is a correct scope, or whether the registry is initialized. 03/18 17:01:11 - mmengine - INFO - Start pipeline mmdeploy.apis.pytorch2onnx.torch2onnx in subprocess 03/18 17:01:12 - mmengine - WARNING - Failed to search registry with scope "mmdet" in the "Codebases" registry tree. As a workaround, the current "Codebases" registry in "mmdeploy" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmdet" is a correct scope, or whether the registry is initialized. 03/18 17:01:12 - mmengine - WARNING - Failed to search registry with scope "mmdet" in the "mmdet_tasks" registry tree. As a workaround, the current "mmdet_tasks" registry in "mmdeploy" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmdet" is a correct scope, or whether the registry is initialized. Loads checkpoint by local backend from path: rtmdet_tiny_8xb32-300e_coco_20220902_112414-78e30dcc.pth The model and loaded state dict do not match exactly
unexpected key in source state_dict: data_preprocessor.mean, data_preprocessor.std
03/18 17:01:12 - mmengine - WARNING - DeprecationWarning: get_onnx_config will be deprecated in the future.
03/18 17:01:12 - mmengine - INFO - Export PyTorch model to ONNX: weights\end2end.onnx.
03/18 17:01:12 - mmengine - WARNING - Can not find torch.nn.functional.scaled_dot_product_attention, function rewrite will not be applied
03/18 17:01:12 - mmengine - WARNING - Can not find mmdet.models.utils.transformer.PatchMerging.forward, function rewrite will not be applied
e:\pycharm\open-mmlab\mmdeploy\mmdeploy\core\optimizers\function_marker.py:160: TracerWarning: Converting a tensor to a Python integer might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
ys_shape = tuple(int(s) for s in ys.shape)
D:\program\Anaconda\envs\openmmlab\lib\site-packages\torch\functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at C:\actions-runner_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\TensorShape.cpp:3191.)
return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined]
e:\pycharm\open-mmlab\mmdeploy\mmdeploy\mmcv\ops\nms.py:477: TracerWarning: Converting a tensor to a Python integer might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
int(scores.shape[-1]),
e:\pycharm\open-mmlab\mmdeploy\mmdeploy\mmcv\ops\nms.py:149: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
out_boxes = min(num_boxes, after_topk)
03/18 17:01:18 - mmengine - ERROR - e:\pycharm\open-mmlab\mmdeploy\mmdeploy\apis\core\pipeline_manager.py - pop_mp_output - 80 - mmdeploy.apis.pytorch2onnx.torch2onnx with Call id: 0 failed. exit.
Reproduction
123
Environment
在通过mmdeploy进行模型转换时遇到了这个问题，有没有大佬给指导一下
Error traceback
No response
