Inference Speeds on Jetson TX2

I was trying to run Detectron2 as an onnx engine- I first turned Detectron2 into .onnx format, then I turned it into a TensorRT engine, when I then tried to run inference on it it ran what I felt was slowly. I was getting about 1.2s inference speeds (per image) with 480x640 image size. I am wondering if that is normal for a Jetson TX2 with TensorRT optimizations? And Is it possible that I can be faster without the TensorRT optimizations.

#Instructions to Reproduce the Issue and Full Logs:
In the TensorRT repo in samples/python/detectron2 run infer.py

## Expected behavior:

I expected it to go much faster - like 0.04 seconds as it does on colab

## Environment:

Provide your environment information using the following command:
I get a syntax error for whatever reason from the command however I'll try my best- Detectron2 built from source, Cuda 10.2, TensorRT 8.2.1, Cudnn- not sure and I'm using a Jetson TX2

Start by running samples/python/detectron2/infer.py in the TensorRT repository on the reported Jetson TX2 environment. Check the inference timing and available environment details against the reported 1.2 seconds per 480x640 image; done means the cause of the discrepancy or expected performance is established with reproducible measurements.

Written by the indexing model from the issue text.