Ross Wightman ad94d737b7 Add support to ConvNextBlock for downsample and channel expansion to improve stand alone use. Fix #1699		2023-03-13 14:06:24 -07:00
..
data	Fix #1713 missed assignement in 3-aug level fn, fix few other minor lint complaints in auto_augment.py	2023-03-11 14:32:23 -08:00
layers	Torchscript fixes/hacks for rms_norm, refactor ParallelScalingBlock with manual combination of input projections, closer paper match	2023-02-16 16:57:42 -08:00
loss	Remove inplace operators when calculating the loss	2022-10-17 10:41:21 +02:00
models	Add support to ConvNextBlock for downsample and channel expansion to improve stand alone use. Fix #1699	2023-03-13 14:06:24 -07:00
optim	Add multi-tensor (foreach) version of Lion in style of upcoming PyTorch 2.0 optimizers	2023-02-16 15:48:00 -08:00
scheduler	Scheduler update, add v2 factory method, support scheduling on updates instead of just epochs. Add LR to summary csv. Add lr_base scaling calculations to train script. Fix #1168	2022-10-07 10:43:04 -07:00
utils	Davit update formatting and fix grad checkpointing (#7)	2023-01-15 14:34:56 -08:00
__init__.py	Major module / path restructure, timm.models.layers -> timm.layers, add _ prefix to all non model modules in timm.models	2022-12-06 15:00:06 -08:00
version.py	Add convnext_xxlarge CLIP image tower weights, version 0.8.15dev0	2023-02-26 21:51:48 -08:00