Skip to content

Train and Inference your custom YOLO-NAS model by Single Command Line

Notifications You must be signed in to change notification settings

fsai-dev/fsai-yolo-nas

 
 

Repository files navigation

Setup

  • Create .comet.config file in base repository dir and add credentials
  • Run make build

Run

  • Check Makefile for specific commands. Commands will differ depending on the machine this will be running on

Train

python train.py --name pylon_complex --data /home/data/bboxes/pylon_complex/yolo/data.yaml --batch 24 --worker 8 --epoch 100 --num_gpus 4

Parameters

  • H100 Gpu:
    • batch size: 24
    • workers: 8

Notes

  • In docker container, you can check super-gradients version by running: python -c 'import super_gradients; print(super_gradients.__version__)'

About

Train and Inference your custom YOLO-NAS model by Single Command Line

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 98.4%
  • Other 1.6%