search

NVIDIA-AI-IOT / trt_pose

Real-time pose estimation accelerated with NVIDIA TensorRT
MIT License
974 stars 291 forks source link

How to train and infer using only a single channel? #131

Closed sinuku closed 3 years ago

sinuku commented 3 years ago

Hi! Thanks for you project. I am trying to train my custom dataset, and inference in jetson nano.

The images in my dataset are single channel images.

I would like to modify the model to use only a single channel.

In this case, could you tell me which part of the model needs to be modified?

Thanks!

sinuku commented 3 years ago

it solved!