Skip to content
This repository was archived by the owner on Dec 15, 2024. It is now read-only.

Tags: ZJCV/ZCls2

Tags

v0.5.3

chore(version): v0.5.3

  1. perf(sampler): when in distribued, set train_sampler be shuffle=True. 80f35da
  2. perf(train.py): add device setting for single GPU training. 932e466
  3. perf(model): update DDP(model) use. c251107

v0.5.2

chore(version): v0.5.2

* New features
  1. build(python): update requirements.txt. aa19609
* Bug fixes
* Breaking changes.

v0.5.1

chore(version): v0.5.1

* New features
  1. build(python): update setup.py INSTALL_REQUIRES. 3ce08a6
  2. fix(setup.py): fix INSTALL_REQUIRES settings. 03050eb
* Bug fixes
* Breaking changes.

v0.5.0

fix(setup.py): fix INSTALL_REQUIRES settings

v0.4.5

chore(version): v0.4.5

* New features
  1. fix(transform): fix Normalize mean/std with max_value use. 51fc80d
* Bug fixes
* Breaking changes.

v0.4.4

chore(version): v0.4.4

* New features
  1. fix(cccf.py): fix class_path load. 3ef83e8
* Bug fixes
* Breaking changes.

v0.4.3

chore(version): v0.4..3

* New features
  1. perf(dataset): update torchvision.dataset.ImageFolder and build.py use. [e95f499](https://github.com/ZJCV/ZCls2/tree/e95f49911cc0d6aea24aba86b1ace8795326eea5)
* Bug fixes
* Breaking changes.

v0.4.2

chore(version): v0.4.2

* New features
  1. feat(transform): add max_value param in _C.TRANSFORM.NORMALIZE. f51f304
* Bug fixes
  1. fix(criterion): fix SoftTargetCrossEntropy use. 04cd13c
* Breaking changes.

v0.4.1

docs(version): v0.4.1

* New features
  1. feat(config): add _C.TRAIN.CALCULATE_ACCURACY. [97f3c79](https://github.com/ZJCV/ZCls2/tree/97f3c79181bc766fa4d6d5330c2c1c1cf709bfa9)
* Bug fixes
  1. fix(trainer.py): fix mixup usage. [1140fe4(https://github.com/ZJCV/ZCls2/tree/1140fe477f25bf0c523d01f060e20b1dac8a2938)
* Breaking changes.

v0.4.0

chore(version): v0.4.0

* New features
  1. perf(misc.py): update resume() to misc.py. [4f417e1](https://github.com/ZJCV/ZCls2/tree/4f417e1941092c8d08c22edf13053e7c231b9790)
  2. perf(parser.py): remove --resume settings. [710791e](https://github.com/ZJCV/ZCls2/tree/710791e63a80c72ea74a742c29d2ef5401c2431d)
  3. feat(tools): add eval.sh. [545e4e4](https://github.com/ZJCV/ZCls2/tree/545e4e41912a6ac0fca33923817d56b0d8a1da0f)
  4. feat(optimizer): add Adam. [7cd0a3a](https://github.com/ZJCV/ZCls2/tree/7cd0a3a2b8b86351b22680b235ca08ba46a2c0aa)
* Bug fixes
  1. fix(train.py): make mixup_fn to train() and update resume() usage. [b5be2ed](https://github.com/ZJCV/ZCls2/tree/b5be2ed3526eb3cb3235c9882a604c8931b01059)
* Breaking changes.

BREAKING CHANGE: