q yao comments

Results 318 comments of


                                            q yao

Improve setup.py

Thanks for the contribution. Please fix the lint check.

[Feature] Add dynamic_scatter op of cpu version from mmdet3d

Please add cpu unit test.

error ocuured when use mmdeploy

Please provide detail about how to reproduce the error.

Fail to build a custom tensorrt plugin

Try export LD_LIBRARY_PATH=${PATH_TO_CUDNN}:$LD_LIBRARY_PATH

Fail to build a custom tensorrt plugin

You have declare ```c++ void attachToContext(cudnnContext *contextCudnn, cublasContext *contextCublas, nvinfer1::IGpuAllocator *gpuAllocator) TRT_NOEXCEPT override; void detachFromContext() TRT_NOEXCEPT override; ``` But no definition in the cpp.

Fail to build a custom tensorrt plugin

The error `undefined symbol: xxx` means that you have declare a function (either added manually or added by template), but forgot to add the definition. You can use `c++filt` to...

Fail to build a custom tensorrt plugin

Close due to no reply. Please feel free to reopen the issue if the problem still exist.

When I use mmdeploy-0.5.0 to run the mask RCNN model on the windows platform, the following error messages appear

Hi, Could you please add `verbose=True` in [onnx_config](https://github.com/open-mmlab/mmdeploy/blob/master/configs/_base_/onnx_config.py) ```python onnx_config = dict( type='onnx', export_params=True, keep_initializers_as_inputs=False, opset_version=11, save_file='end2end.onnx', input_names=['input'], output_names=['output'], verbose=True, input_shape=None) ``` Which would give you more detail about the...

When I use mmdeploy-0.5.0 to run the mask RCNN model on the windows platform, the following error messages appear

Errr, theoretically the export would give you the graph information when verbose=True. But It is not in your log. Could you please try to convert a simple model such as...

When I use mmdeploy-0.5.0 to run the mask RCNN model on the windows platform, the following error messages appear

Most models in MMDetection use custom ops in MMCV. I want to known if the error is caused by these ops. So please try convert a simple model like resnet...