Ross Wightman 4d5c395160 MaxVit, ViT, ConvNeXt, and EfficientNet-v2 updates ...

* Add support for TF weights and modelling specifics to MaxVit (testing ported weights)
* More fine-tuned CLIP ViT configs
* ConvNeXt and MaxVit updated to new pretrained cfgs use
* EfficientNetV2, MaxVit and ConvNeXt high res models use squash crop/resize

2022-12-05 10:21:34 -08:00

..

data

Switch TFDS dataset to use INTEGER_ACCURATE jpeg decode by default

2022-12-05 10:21:34 -08:00

loss

Remove inplace operators when calculating the loss

2022-10-17 10:41:21 +02:00

models

MaxVit, ViT, ConvNeXt, and EfficientNet-v2 updates

2022-12-05 10:21:34 -08:00

optim

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

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

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

__init__.py

Initial multi-weight support, handled so old pretraing config handling co-exists with new tags.

2022-12-05 10:21:34 -08:00

version.py

Version 0.7.dev0 for master

2022-10-14 09:38:02 -07:00