SegFormer Backbones Available

Accelerated Computing Intelligent Video Analytics TAO Toolkit
1

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

Slightly confused by TAO4.01; in earlier versions you download a pretrained model as the backbone. In version 4.01 i was trying to use the segformer model and appears that you specify the backbone in the spec file for training?

Cheers

2

For 4.0.1

it is the same as 4.0.0.

model_config:
pretrained: /path/to/your-pretrained-backbone-model
backbone:
type: “mit_b5”

3

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