optax-adan
An implementation of adan optimizer for optax based on Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models.
Collab with usage example can be found here.
How to use:
Install the package:
python3 -m pip install optax-adan
Import the optimizer:
from optax_adan import adan
Use it as you would use any other optimizer from optax:
# init
optimizer = adan(learning_rate=0.01)
optimizer_state = optimizer.init(initial_params)
# step
grad = grad_func(params)
updates, optimizer_state = optimizer.update(grad, optimizer_state, params)
params = optax.apply_updates(params, updates)
1 maintainer
Metadata
1 maintainer
Release files for optax-adan 0.1.5
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| optax-adan-0.1.5.tar.gz | 7.7 kB | Details |
Release files / optax-adan-0.1.5.tar.gz
| Download URL | optax-adan-0.1.5.tar.gz |
|---|---|
| Size | 7.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
a0a7de368d3b84f5b61f36293945d6d64b30fa284c2098f74fc21349a6273d38
|
|
BLAKE2b-256 checksum How to use checksums |
4a804423ad06bd3bc95e8bd16a0d487abe50193e33d920be7df7aa0a56b5de28
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.1 CPython/3.9.13
|
