Jean B
jbegaint
·
AI & ML interests
None yet
Recent Activity
reacted
to
rwightman's
post
with 🚀
21 days ago
There's a new `timm` release, v 1.0.12, with a focus on optimizers. The optimizer factory has been refactored, there's now a `timm.optim.list_optimizers()` and new way to register optimizers and their attributes. As always you can use an `timm` optimizer like a `torch` one, just replace `torch.optim` with `timm.optim`
New optimizers include:
* AdafactorBigVision - `adfactorbv`
* ADOPT - `adopt` / `adoptw` (decoupled decay)
* MARS - `mars`
* LaProp - `laprop`
* Cautious Optimizers - a modification to all of the above, prefix with `c` as well as `cadamw`, `cnadamw`, `csgdw`, `clamb`, `crmsproptf`
I shared some caution comparisons in this model repo: https://huggingface.co/rwightman/timm-optim-caution
For details, references, see the code: https://github.com/huggingface/pytorch-image-models/tree/main/timm/optim
Organizations
