ONNX-TensorRT : Engine Creation using custom layer and score layer for ONNX model.
Environment :
TensorRT Version : 7
GPU Type :
Nvidia Driver Version :
CUDA Version : 10.0.3
CUDNN Version : 7.6.5
Operating System + Version : Windows 10
Python Version (if applicable) : Using C++ with ONNX
TensorFlow Version (if applicable) : 2.2.0
PyTorch Version (if applicable) :
Baremetal or Container (if container which image + tag) :
TensorRT Engine Creation using Onnx Model:
- I have to save the Engine file by marking the output layer to the following:
(a) res4b
(b) score3 - I am able to do this using the caffeparser in c++, but I am not able to do in onnxParser.
Please do the needful and oblige.