Skip to main content

AdaBound optimizer in Keras

Project description

Keras AdaBound

Travis Coverage

AdaBound optimizer in Keras.

Install

pip install keras-adabound

Usage

Use the optimizer

from keras_adabound import AdaBound

model.compile(optimizer=AdaBound(lr=1e-3, final_lr=0.1), loss=model_loss)

Load with custom objects

from keras_adabound import AdaBound

model = keras.models.load_model(model_path, custom_objects={'AdaBound': AdaBound})

About weight decay

The optimizer does not have an argument named weight_decay (as in the official repo) since it can be done by adding L2 regularizers to weights:

import keras

regularizer = keras.regularizers.l2(WEIGHT_DECAY / 2)
for layer in model.layers:
    for attr in ['kernel_regularizer', 'bias_regularizer']:
        if hasattr(layer, attr) and layer.trainable:
            setattr(layer, attr, regularizer)

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Files for keras-adabound, version 0.5.0
Filename, size File type Python version Upload date Hashes
Filename, size keras-adabound-0.5.0.tar.gz (4.9 kB) File type Source Python version None Upload date Hashes View

Supported by

Pingdom Pingdom Monitoring Google Google Object Storage and Download Analytics Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN DigiCert DigiCert EV certificate StatusPage StatusPage Status page