pytorch-auto-drive icon indicating copy to clipboard operation
pytorch-auto-drive copied to clipboard

Published 20 hours ago • verified publisher icon voldemortX

TensorRT

Open liuYYYYYYYYy opened this issue 2 years ago • 6 comments

What should I do after generating the TensorRT model?

liuYYYYYYYYy avatar May 24 '22 07:05 liuYYYYYYYYy

@liuYYYYYYYYy You can use it in NVIDIA's related packages. I believe there is pip inference toolkits like tensorrt. See https://developer.nvidia.com/tensorrt for introductions.

voldemortX avatar May 24 '22 08:05 voldemortX

Is there no code in this project that can run TensorRT model？

liuYYYYYYYYy avatar May 24 '22 08:05 liuYYYYYYYYy

@liuYYYYYYYYy Currently we only provide conversion codes. However, we do have some verification codes that does inference here. You could use it similarly like here.

In the future, we might want to provide onnx/tensorrt execution for full dataset/custom input inference or visualization processes.

voldemortX avatar May 24 '22 08:05 voldemortX

Hi @voldemortX Seniors! Is the FPS of the model in the repository, using TensorRT?

Rsweater avatar Dec 20 '22 02:12 Rsweater

@Rsweater Not yet, lots of them have conversion issues and I feel like it should be done on a jetson, which I don't have.

voldemortX avatar Dec 20 '22 02:12 voldemortX

@Rsweater Not yet, lots of them have conversion issues and I feel like it should be done on a jetson, which I don't have.

Oh, I see. Thank you very much, senior.

Rsweater avatar Dec 20 '22 07:12 Rsweater