7 Commits (48371a33b11fc30ca23ed8988619af08902b215b)

Author	SHA1	Message	Date
Ross Wightman	5a8e1e643e	Initial Normalizer-Free Reg/ResNet impl. A bit of related layer refactoring.	4 years ago
Ross Wightman	110a7c4982	AdaptiveAvgPool2d -> mean((2,3)) for all SE/attn layers to avoid NaN with AMP + channels_last layout. See https://github.com/pytorch/pytorch/issues/43992	4 years ago
Ross Wightman	3b6cce4c95	Add initial impl of CrossStagePartial networks, yet to be trained, not quite the same as darknet cfgs.	5 years ago
Ross Wightman	4ddde1d3a4	Fix two regressions	5 years ago
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	5 years ago
Ross Wightman	50658b9a67	Add RegNet models and weights	5 years ago
Ross Wightman	f902bcd54c	Layer refactoring continues, ResNet downsample rewrite for proper dilation in 3x3 and avg_pool cases ... * select_conv2d -> create_conv2d * added create_attn to create attention module from string/bool/module * factor padding helpers into own file, use in both conv2d_same and avg_pool2d_same * add some more test eca resnet variants * minor tweaks, naming, comments, consistency	5 years ago