Segformer AutoML Spec file

Please provide the following information when requesting support.

• Hardware (T4/V100/Xavier/Nano/etc) A6000
• Network Type (Detectnet_v2/Faster_rcnn/Yolo_v4/LPRnet/Mask_rcnn/Classification/etc) Segformer
• TLT Version (Please run “tlt info --verbose” and share “docker_tag” here)
• Training spec file(If have, please share here)
• How to reproduce the issue ? (This is for errors. Please share the command line and the detailed log here.)

Hi,

Can you please provide information regarding the spec file for AutoML (wandb) to allow use with Segformer. Recent videos suggest the Segformer is now available with AutoML - please see image.

Cheers

For running AutoML, it is needed to setup TAO API. Refer to AutoML - NVIDIA Docs. The related notebooks of “TAO-API” are different from “TAO launcher”.

TAO-API: tao_tutorials/notebooks/tao_api_starter_kit at main · NVIDIA/tao_tutorials · GitHub
TAO-launcher:
tao_tutorials/notebooks/tao_launcher_starter_kit at main · NVIDIA/tao_tutorials · GitHub

The segformer notebook under TAO-API can be found in tao_tutorials/notebooks/tao_api_starter_kit/api/segmentation.ipynb at main · NVIDIA/tao_tutorials · GitHub.

Thank you @Morganh for the very swift and full response.

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