CyberZHG/keras-radam
RAdam implemented in Keras & TensorFlow
| repo name | CyberZHG/keras-radam |
| repo link | https://github.com/CyberZHG/keras-radam |
| homepage | https://pypi.org/project/keras-rectified-adam/ |
| language | Python |
| size (curr.) | 63 kB |
| stars (curr.) | 292 |
| created | 2019-08-16 |
| license | MIT License |
Keras RAdam
Unofficial implementation of RAdam in Keras and TensorFlow.
Install
pip install keras-rectified-adam
External Link
Usage
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)
TensorFlow without Keras
from keras_radam.training import RAdamOptimizer
RAdamOptimizer(learning_rate=1e-3)
Use Warmup
from keras_radam import RAdam
RAdam(total_steps=10000, warmup_proportion=0.1, min_lr=1e-5)
Q & A
About Correctness
The optimizer produces similar losses and weights to the official optimizer after 500 steps.
Use tf.keras or tf-2.0
Add TF_KERAS=1 to environment variables to use tensorflow.python.keras.
Use theano Backend
Add KERAS_BACKEND=theano to environment variables to enable theano backend.
