super-gradients

Easily train or fine-tune SOTA computer vision models with one open source training library. The home of Yolo-NAS.

APACHE-2.0 License

Downloads
38K
Stars
4.3K
Committers
60
View Code on GitHub Visit Website
Ecosystems: Jupyter Notebook

Bot releases are hidden (Show)

super-gradients - 3.0.5

Published by shaydeci almost 2 years ago

What's Changed

Full Changelog: https://github.com/Deci-AI/super-gradients/compare/3.0.4...3.0.5

super-gradients - 3.0.4

Published by deci-services almost 2 years ago

What's Changed

Full Changelog: https://github.com/Deci-AI/super-gradients/compare/3.0.3...3.0.4

super-gradients -

Published by deci-services almost 2 years ago

  • ClearML integration.
  • Console logging + upload (Lab visibility).
  • Epoch summary (visual improvement).
  • Registry for Phase Callbacks and Transforms.
  • Infrastructure for crash tips.
  • Detection output adapter.
  • Train from recipe example- external dataset.
  • QAT infrastructure + examples.
  • System Logger (i.e device attributes etc).
super-gradients - 3.0.2

Published by deci-services almost 2 years ago

  • dataloaders.get() supports Dataset objects.
  • Behind the scenes sampler handling (warning + initialization).
  • Black formatter.
  • New DetectionBase.
  • Logs moved from ~/sg_log/{module_name}
  • CSP Resnet Backbone, new place for modules in repo.
  • Plenty new factories.
  • Message on effective batch size
  • External checkpoints resume- fix
  • Passing external classes list for CocoDetection
  • Fix for loading weights from the platform
super-gradients -

Published by deci-services about 2 years ago

What's new?

  • Eval recipe- perform validation by recipe name.
  • Supported strings class for convenient autocomplete in IDE's.
  • Registry: metrics, dataloaders, models, losses (so they can be passed as strings when using train_from_config).
  • Return model, results from train
  • Load backbone fix https://github.com/Deci-AI/super-gradients/pull/408/files
  • PPLiteSeg training recipes.
  • AWS env check removal
  • New resolvers support: "+" "if" for yaml recipes (i.e Hydra resolvers).
  • Support for custom STDC.
  • ShelfNet "classes_num" -> "num_classes" bug fix.
  • Improve cross-platform compatibility when parsing a readme description.
  • Added the ability to download and import external code for models from ADK.
super-gradients - 3.0.0

Published by deci-services about 2 years ago

  • DatasetInterface class removal- refactored as torch.DataLoader objects configured by src/training/recipes, using super_gradients.dataloaders.get() (see new updated tutorials and snippets).

  • Trainer.build_model() removal- models initialisation refactored with super_gradients.models.get() (see updated tutorials and notebooks).

  • Coded DDP launch (no need for python -m torch.distributed.launch ...), see new snippets here .

  • Updated notebooks, tutorials and code snippets in readme.md.

  • Extract recipes training hyper_params config with super_gradients.training_hyperparams.get() (see updated tutorials and notebooks).

  • Simplfied resume- now passed through train_params in SgTrainer.train() (see updated snippets in readme.md).

  • Removal of "loss_loggging_items_names" from train_params in Trainer.train().

  • Trainer.init old, unnecessary args removed.

  • Add support for getting models from Deci's platform using super_gradients.models.get(), more info regarding Deci's platform in readme.md.

super-gradients - https://github.com/Deci-AI/super-gradients/releases/tag/2.6.0

Published by deci-services about 2 years ago

This GitHub Release was done automatically by CircleCI

super-gradients - https://github.com/Deci-AI/super-gradients/releases/tag/2.5.0

Published by deci-services about 2 years ago

This GitHub Release was done automatically by CircleCI

super-gradients - https://github.com/Deci-AI/super-gradients/releases/tag/2.2.0

Published by deci-services about 2 years ago

This GitHub Release was done automatically by CircleCI

super-gradients - 2.1.0

Published by deci-services over 2 years ago

  • YoloX architectures.
  • SSDLite Mobilenet V2 COCO recipe
  • QAT support with Nvidia's pytorch-quantization (optional dependency).
  • COCO mAP calculation support in DDP (torch metric object, supports "crowd" labels).
  • Pre_prediction_callback- support for input and targets manipulation right before forward pass + multiscaling pre_prediction_callbacks that work out of the box in DDP (classification and Object detection).
  • Training stage switch callback to support multi-stage training.
super-gradients - https://github.com/Deci-AI/super-gradients/releases/tag/2.0.1

Published by deci-services over 2 years ago

This GitHub Release was done automatically by CircleCI

super-gradients - 2.0.0

Published by deci-services over 2 years ago

Features:

  • KD trainer and resnet50 recipe (81.92 % accuracy)
  • Repeated augmentation sampler
  • Cooldown epochs
  • Beit architecture
  • Lamb Optimizer
  • Passing torch data loaders directly to SgModel.

Refactoring:

  • Checkpoint and architecture params decoupled.
super-gradients - 1.7.5

Published by deci-services over 2 years ago

  • STDC architectures binary segmentation support bug fix.
super-gradients - 1.7.4

Published by deci-services over 2 years ago

torchmetrics version requirement set to 0.7.3 to avoid metric names depreciation bug.

super-gradients - https://github.com/Deci-AI/super-gradients/releases/tag/1.7.3

Published by deci-services over 2 years ago

This GitHub Release was done automatically by CircleCI

super-gradients - https://github.com/Deci-AI/super-gradients/releases/tag/1.7.2

Published by deci-services over 2 years ago

This GitHub Release was done automatically by CircleCI

super-gradients - 1.7.1

Published by deci-services over 2 years ago

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
  • Google Colab notebook for semantic segmentation transfer learning - Check it out in our GitHub repo README.md
super-gradients -

Published by shaydeci over 2 years ago

super-gradients - 1.6.0

Published by deci-services over 2 years ago

  • Added RegSeg model, recipe, and pre-trained checkpoints.
  • Updated EfficientNet recipe.
  • Updated Resnet50 recipe + pre-trained checkpoint (Top-1=79.47)
super-gradients - 1.5.2

Published by deci-services over 2 years ago

  • Detection visualisation callback, wrong color ordering for images in tensor board fix.
Package Rankings
Top 3.57% on Pypi.org
Badges
Extracted from project README
Tweet Open In Colab Open In Colab Open In Colab Open In Colab Open In Colab Open In Colab Open In Colab Open In Colab Open In Colab Open In Colab Open In Colab Open In Colab Open In Colab Open In Colab Open In Colab Open In Colab Open In Colab Open In Colab Open In Colab DOI
Related Projects
ProtTrans

ProtTrans is providing state of the art pretrained language models for proteins. ProtTrans was tr...

11 May 2020 1,099
mxnet-the-straight-dope

An interactive book on deep learning. Much easy, so MXNet. Wow. [Straight Dope is growing up] ---...

11 Jul 2017 2,560
dl-colab-notebooks

Try out deep learning models online on Google Colab

12 Mar 2019 1,715
big_vision

Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.

04 Apr 2022 2,245
taming-transformers

Taming Transformers for High-Resolution Image Synthesis

17 Dec 2020 5,727
awesome-AI-books

Some awesome AI related books and pdfs for learning and downloading, also apply some playground m...

25 Feb 2018 1,287