Skip to main content

A wrapper that slows down the updates of trainable weights

Project description

Keras Successive Regularization Wrapper

Travis Coverage

A wrapper that slows down the updates of trainable weights.


pip install keras-succ-reg-wrapper


import keras
from keras_succ_reg_wrapper import SuccReg

input_layer = keras.layers.Input(shape=(1,), name='Input')
dense_layer = SuccReg(
    layer=keras.layers.Dense(units=1, name='Dense'),
    regularizer=keras.regularizers.L1L2(l2=1e-3),  # Any regularizer
model = keras.models.Model(inputs=input_layer, outputs=dense_layer)
model.compile(optimizer='adam', loss='mse')

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-succ-reg-wrapper-0.4.0.tar.gz (2.9 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