keras-targeted-dropout 0.3.0

Targeted dropout implemented in Keras

Implementation of Targeted Dropout with tensorflow backend.

Install

pip install keras-targeted-dropout

Usage

import keras
from keras_targeted_dropout import TargetedDropout

model = keras.models.Sequential()
model.add(TargetedDropout(input_shape=(None, None), drop_rate=0.4, target_rate=0.4))
model.compile(optimizer='adam', loss='mse')
model.summary()

• drop_rate: Dropout rate for each pixel.

• target_rate: The proportion of bottom weights selected as candidates per channel.

The final dropout rate will be drop_rate times target_rate.

See Fashion MNIST demo.