You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

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		4 years ago
..
data	added MultiEpochsDataLoader	5 years ago
loss	Update AugMix, JSD, etc comments and references	5 years ago
models	Monster commit, activation refactor, VoVNet, norm_act improvements, more	4 years ago
optim	Add 'momentum' optimizer (SGD w/o nesterov) for stable EfficientDet training defaults	5 years ago
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.	5 years ago
__init__.py	Monster commit, activation refactor, VoVNet, norm_act improvements, more	4 years ago
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	5 years ago
version.py	Fix #139. Broken SKResNets after BlurPool addition, as a plus, SKResNets support AA now too.	5 years ago