/ Machine Learning

Keras implementation of Attention Augmented Convolutional Neural Networks

Keras implementation of Attention Augmented Convolutional Neural Networks

Keras Attention Augmented Convolutions

A Keras (Tensorflow only) wrapper over the Attention Augmentation module from the paper Attention Augmented Convolutional Networks.

Provides a Layer for Attention Augmentation as well as a callable function to build a augmented convolution block.

attention-augmented-convs

Usage

It is advisable to use the augmented_conv2d(...) function directly to build an attention augmented convolution block.

from attn_augconv import augmented_conv2d

ip = Input(...)
x = augmented_conv2d(ip, ...)
...

If you wish to add the attention module seperately, you can do so using the AttentionAugmentation2D layer as well.

from attn_augconv import AttentionAugmentation2D

ip = Input(...)

# make sure that input to the AttentionAugmentation2D layer has (2 * depth_k + depth_v) filters.
x = Conv2D(2 * depth_k + depth_v, ...)(ip)
x = AttentionAugmentation2D(depth_k, depth_v, num_heads)(x)
...

Requirements

  • Keras 2.2.4+
  • Tensorflow 1.13+ (2.0 not tested yet)

GitHub