q yao

Hi, I do not find any TensorRT related heads or libs (NvInfer* or libnvinfer* ) in `nvcr.io/nvidia/deepstream-l4t:5.0.1-20.09-samples`

Did that mean the container will use TensorRT and other Dependent libraries from the host?

I am not sure. I found a similar error in other repos with [solution](https://github.com/traveller59/spconv/issues/21#issuecomment-495889887), see if it can help you.

And tensorrt 7.0 is not recommended. It might meet memory leak on some device.

If you are using [mmdetection-to-tensorrt](https://github.com/grimoire/mmdetection-to-tensorrt) to convert model. The inference interface is in [here](https://github.com/grimoire/mmdetection-to-tensorrt/blob/master/mmdet2trt/apis/inference.py), not the official one. [here](https://github.com/grimoire/mmdetection-to-tensorrt/blob/master/demo/inference.py) is the demo. I haven't tested the repo on mmdetection2.13，if you...

This might help you with your problem [link](https://github.com/grimoire/mmdetection-to-tensorrt/blob/master/docs/FAQ.md#q-error-parameter-check-failed-at-enginecppsetbindingdimensions1046-condition-profilemindimsdi--dimensionsdi)

Hi Seems like something wrong with the custom plugin. did you install [https://github.com/grimoire/amirstan_plugin](https://github.com/grimoire/amirstan_plugin) ? Don't forget to add the eviroment vairable. It you did install the plugin correctly, please provide...

Hi, [here](https://github.com/grimoire/mmdetection-to-tensorrt/tree/master/demo/cpp) is a c++ example of engine deployment. See if this can help you.

could you check if third_party/cub is empty or not? if it is empty , use `git submodule update --init` to pull the sub module or you can download cub by...

Hi Thanks for the bug report. The interpolate layer is implemented by IResizeLayer in TRT. I did found there are some different between pytorch and TRT in NEAREST mode. There...