super-gradients

• Minor fixes for transfer learning example notebook support.

What’s new?

• STDC family - new recipes added with even higher mIoU💪

• Google Colab notebook for transfer learning / fine-tuning (COCO pre-trained YOLOv5 nano into PASCAL VOC sub dataset) - Check it out in our GitHub repo README.md

• Factories for yaml string interpolation

• Transfer learning example added for YoloV5.
• Optional checkpoint root directory path argument added to SgModel.
• Regnet recipes updated.

Checkpoints root directory fix- allowing users to explicitly define checkpoints root directory instead of depriving it from content root.

• Upload to pipy added to ci workflow.
• Max epochs limitation removed.
• Post training phase moved before closing loggers

• Added an option to upload any file from the checkpoint dir.
• Added a new callback phase and calling it on best metric.
• Automatic GPU mode for training recipes.
• Readme updates.
• Sphinx documentation updates.

This GitHub Release was done automatically by CircleCI

-Pretrained classification models with head replacement
-Quickstart notebook added
-Optionally loading EMA net for testing