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 and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page