Adding Tensorrt Plugin to Deserialized Engine

I have a YOLO network in Caffe format, building the network as engine is succesful and I can infer with it. However I also want to migrate the preprocessing part (resizing and cropping) to TRT too. Guess i need to use cropAndResize Plugin but couldnt find a way to “attach” it to my pipeline.

Thanks in advance.

Environment

TensorRT Version: 7.0.0.11
GPU Type: RTX 2070 Mobile
Nvidia Driver Version: 460
CUDA Version: 10.0
CUDNN Version: 7.6
Operating System + Version: Ubuntu 18.04

Hi @orcdnz,

Hope following links will help you.
https://docs.nvidia.com/deeplearning/tensorrt/sample-support-guide/index.html#plugin_sample

Thank you.

Hi, Request you to check the below reference links for custom plugin implementation.

Thanks!

Thanks but i was actually looking for a way to use plugins that are already existing in TRT. Preferably without modifying the CAFFE model itself. Any further recommendations?

Hi @orcdnz,

Please refer the following doc.
https://docs.nvidia.com/deeplearning/tensorrt/sample-support-guide/index.html

Thank you.