Ross Wightman eb7653614f Monster commit, activation refactor, VoVNet, norm_act improvements, more ...

* refactor activations into basic PyTorch, jit scripted, and memory efficient custom auto
* implement hard-mish, better grad for hard-swish
* add initial VovNet V1/V2 impl, fix #151
* VovNet and DenseNet first models to use NormAct layers (support BatchNormAct2d, EvoNorm, InplaceIABN)
* Wrap IABN for any models that use it
* make more models torchscript compatible (DPN, PNasNet, Res2Net, SelecSLS) and add tests

2020-06-01 17:16:52 -07:00

..

data

added MultiEpochsDataLoader

2020-05-05 14:47:02 +03:00

loss

Update AugMix, JSD, etc comments and references

2020-01-11 12:02:05 -08:00

models

Monster commit, activation refactor, VoVNet, norm_act improvements, more

2020-06-01 17:16:52 -07:00

optim

Add 'momentum' optimizer (SGD w/o nesterov) for stable EfficientDet training defaults

2020-04-25 19:42:13 -07:00

scheduler

Fix memory_efficient mode for DenseNets. Add AntiAliasing (Blur) support for DenseNets and create one test model. Add lr cycle/mul params to train args.

2020-05-22 16:16:45 -07:00

__init__.py

Monster commit, activation refactor, VoVNet, norm_act improvements, more

2020-06-01 17:16:52 -07:00

utils.py

Remove poorly named metrics from torch imagenet example origins. Use top1/top5 in csv output for consistency with existing validation results files, acc elsewhere. Fixes #111

2020-04-10 14:41:08 -07:00

version.py

Fix #139. Broken SKResNets after BlurPool addition, as a plus, SKResNets support AA now too.

2020-05-04 12:14:43 -07:00