Can we use tlt-converter and tao-converter interchangeably?

Accelerated Computing Intelligent Video Analytics TAO Toolkit
1

Please provide the following information when requesting support.

• Hardware (T4/V100/Xavier/Nano/etc): GeForce 3090
• Network Type (Detectnet_v2/Faster_rcnn/Yolo_v4/LPRnet/Mask_rcnn/Classification/etc) : Yolo_v4
• TLT Version (Please run “tlt info --verbose” and share “docker_tag” here): TAO Toolkit 3.0-21.11
• Training spec file(If have, please share here): N/A
• How to reproduce the issue ? (This is for errors. Please share the command line and the detailed log here.): N/A

I have a .tlt file train in TAO Toolkit 3.0, I convert it using the old tlt-converter and the new tao-converter (both for cuda111-cudnn80-trt72) and both converter works. Is there a different between these two converters or the difference is a name change from tlt 3.0 to tao 3.0?

2

It is the name changing.
But tlt-converter is the old version. So it may not be compatible with the environment which has TRT8.

3

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.