Super-gradients

What's new ?

- BCE with Dice loss.
- Binary IOU metric object (I.e IOU only for target class).
- Binary segmentation visualisation callback.
- Supervisely dataset interface.
- Different lr assignment for head and backbone for RegSeg.
- Google Colab notebook for semantic segmentation quick start - Check it out in our GitHub repo [README.md](https://github.com/Deci-AI/super-gradients#quick-start-notebook---semantic-segmentation)
- Google Colab notebook for semantic segmentation transfer learning - Check it out in our GitHub repo [README.md](https://github.com/Deci-AI/super-gradients#transfer-learning-with-sg-notebook---semantic-segmentation)

- Added RegSeg model, recipe, and pre-trained checkpoints.
- Updated EfficientNet recipe.
- Updated Resnet50 recipe + pre-trained checkpoint (Top-1=79.47)

- Detection visualisation callback, wrong color ordering for images in tensor board fix.

- Minor fixes for transfer learning example notebook support.

What’s new?

- STDC family - new recipes added with even higher mIoU:muscle:

- 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](https://github.com/Deci-AI/super-gradients/blob/master/README.md)

- Factories for yaml string interpolation