Keras RAdam
Unofficial implementation of RAdam in Keras.
Install
pip install keras-rectified-adam
External Link
Usage
from tensorflow import keras
import numpy as np
from keras_radam import RAdam
# Build toy model with RAdam optimizer
model = keras.models.Sequential()
model.add(keras.layers.Dense(input_shape=(17,), units=3))
model.compile(RAdam(), loss='mse')
# Generate toy data
x = np.random.standard_normal((4096 * 30, 17))
w = np.random.standard_normal((17, 3))
y = np.dot(x, w)
# Fit
model.fit(x, y, epochs=5)
Use Warmup
from keras_radam import RAdam
RAdam(total_steps=10000, warmup_proportion=0.1, min_lr=1e-5)
1 maintainer
Release files for keras-rectified-adam 0.20.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| keras-rectified-adam-0.20.0.tar.gz | 7.0 kB | Details |
Release files / keras-rectified-adam-0.20.0.tar.gz
| Download URL | keras-rectified-adam-0.20.0.tar.gz |
|---|---|
| Size | 7.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
649102f602a79d5f971d227e7defb432302e0b19b3acf48002a6304a5f376a3a
|
|
BLAKE2b-256 checksum How to use checksums |
64ee5a1eaf6e6fc907ef871bc6241d97ecb55936b112c0cbb93e5df1268bca64
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.4.1 importlib_metadata/4.0.1 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.60.0 CPython/3.6.13
|
