Skip to main content

Lookahead mechanism for optimizers in Keras

Project description

Keras Lookahead

Travis Coverage Version Downloads License

[中文|English]

Unofficial implementation of the lookahead mechanism for optimizers.

Install

pip install keras-lookahead

External Links

Usage

Arguments:

  • optimizer: Original optimizer.
  • sync_period: the k in the paper. The synchronization period.
  • slow_step: the α in the paper. The step size of slow weights.
from keras_lookahead import Lookahead

optimizer = Lookahead('adam', sync_period=5, slow_step=0.5)

Custom optimizers can also be used:

from keras_radam import RAdam
from keras_lookahead import Lookahead

optimizer = Lookahead(RAdam())

Project details


Download files

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

Source Distribution

keras-lookahead-0.9.0.tar.gz (5.3 kB view hashes)

Uploaded source

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring Facebook / Instagram Facebook / Instagram PSF Sponsor Fastly Fastly CDN Google Google Object Storage and Download Analytics Huawei Huawei PSF Sponsor Microsoft Microsoft PSF Sponsor NVIDIA NVIDIA PSF Sponsor Pingdom Pingdom Monitoring Salesforce Salesforce PSF Sponsor Sentry Sentry Error logging StatusPage StatusPage Status page