Sesemi

What's Changed
* Refactor the configs to support self-superised pretraining and add torchvision backbones by tigist-d in https://github.com/FlyreelAI/sesemi/pull/43
* Fixes EMA update in fully supervised mode by tigist-d in https://github.com/FlyreelAI/sesemi/pull/44
* Improve logging support by tigist-d in https://github.com/FlyreelAI/sesemi/pull/45
* Refactor datasets by tigist-d in https://github.com/FlyreelAI/sesemi/pull/46
* Enforce a naturally sorted build order for loss heads by tigist-d in https://github.com/FlyreelAI/sesemi/pull/47
* Add optional kNN evaluation support by tigist-d in https://github.com/FlyreelAI/sesemi/pull/48
* Improve data loading with mix of small and large datasets by tigist-d in https://github.com/FlyreelAI/sesemi/pull/49
* Enforce naming conventions throughout the codebase by tigist-d in https://github.com/FlyreelAI/sesemi/pull/50
* Fix support for unbounded iterable datasets by tigist-d in https://github.com/FlyreelAI/sesemi/pull/51
* Add a class-weighted (e.g. balanced) dataset wrapper by tigist-d in https://github.com/FlyreelAI/sesemi/pull/52
* Refactor dataset and loss head modules by tigist-d in https://github.com/FlyreelAI/sesemi/pull/53
* Various fixes and improvements resulting from testing by tigist-d in https://github.com/FlyreelAI/sesemi/pull/54
* Add unit test suite by tigist-d in https://github.com/FlyreelAI/sesemi/pull/55
* Update documentation and enable automated builds using readthedocs by tigist-d in https://github.com/FlyreelAI/sesemi/pull/56
* Upgrade Python version and include sesemi as a requirement in the readthedocs build by tigist-d in https://github.com/FlyreelAI/sesemi/pull/57


**Full Changelog**: https://github.com/FlyreelAI/sesemi/compare/v0.3.0...v1.0.0b1

Release Notes
---
* Support new dataset formats (CIFAR-10/100, STL, and more).
* Support pseudo-label dataset generation.
* Add new SSL methods including consistency regularization, FixMatch, and noisy student.
* Fixes and improvements.

What's Changed
* Ensures that the unsup subset is included in the configs using imagewang by tigist-d in https://github.com/FlyreelAI/sesemi/pull/25
* Add support for consistency regularization (Pi Model) by vuptran in https://github.com/FlyreelAI/sesemi/pull/27
* Add EMA consistency regularization (Mean Teacher) by vuptran in https://github.com/FlyreelAI/sesemi/pull/28
* Move EMA config into model config and include logs by tigist-d in https://github.com/FlyreelAI/sesemi/pull/30
* Add CIFAR-10, CIFAR-100, and STL-10 datasets and baseline models by tigist-d in https://github.com/FlyreelAI/sesemi/pull/29
* Add FixMatch loss head by tigist-d in https://github.com/FlyreelAI/sesemi/pull/31
* Add support for pseudo-labeled dataset generation by tigist-d in https://github.com/FlyreelAI/sesemi/pull/32
* Add noisy student training configurations by tigist-d in https://github.com/FlyreelAI/sesemi/pull/33
* Fix minor issues with docs by tigist-d in https://github.com/FlyreelAI/sesemi/pull/34


**Full Changelog**: https://github.com/FlyreelAI/sesemi/compare/v0.2.0...v0.3.0

Release Notes
---
* Add new pretext methods including entropy minimization and jigsaw prediction along with various different combinations.
* Add support for shared heads and structure configurations hierarchical for ease of reuse.
* Fixes and improvements.

Release Notes
---
* Mitigate issues when using torch version 1.9.
* Improve documentation.

Release Notes
---
* Supports both DP and DDP training using PyTorch Lightning.
* Supports Hydra for configuration management.
* Contains pretext rotation prediction self-supervised regularization.