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
477a78ed81
Fix optimizer factory regressin for optimizers like sgd/momentum that don't have an eps arg
|
4 years ago |
| .. |
|
__init__.py
|
Add Adafactor and Adahessian optimizers, cleanup optimizer arg passing, add gradient clipping support.
|
4 years ago |
|
adafactor.py
|
Add Adafactor and Adahessian optimizers, cleanup optimizer arg passing, add gradient clipping support.
|
4 years ago |
|
adahessian.py
|
Add Adafactor and Adahessian optimizers, cleanup optimizer arg passing, add gradient clipping support.
|
4 years ago |
|
adamp.py
|
Add `adamp` and 'sgdp' optimizers.
|
4 years ago |
|
adamw.py
|
Add RAdam, NovoGrad, Lookahead, and AdamW optimizers, a few ResNet tweaks and scheduler factory tweak.
|
5 years ago |
|
lookahead.py
|
Fix some attributions, add copyrights to some file docstrings
|
4 years ago |
|
nadam.py
|
Big re-org, working towards making pip/module as 'timm'
|
5 years ago |
|
novograd.py
|
Add RAdam, NovoGrad, Lookahead, and AdamW optimizers, a few ResNet tweaks and scheduler factory tweak.
|
5 years ago |
|
nvnovograd.py
|
Add Nvidia's NovogGrad impl from Jasper (cleaner/faster than current) and Apex Fused optimizers
|
5 years ago |
|
optim_factory.py
|
Fix optimizer factory regressin for optimizers like sgd/momentum that don't have an eps arg
|
4 years ago |
|
radam.py
|
Add RAdam, NovoGrad, Lookahead, and AdamW optimizers, a few ResNet tweaks and scheduler factory tweak.
|
5 years ago |
|
rmsprop_tf.py
|
Fix some attributions, add copyrights to some file docstrings
|
4 years ago |
|
sgdp.py
|
Add `adamp` and 'sgdp' optimizers.
|
4 years ago |
