Skip to content
Keras w/ Tensorflow backend implementation for 3D channel-wise convolutions
Python
Branch: master
Clone or download
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
images
.gitignore Initial commit Jun 3, 2019
DepthwiseConv3D.py Update for kernel dim and group support - v0.1 Aug 9, 2019
LICENSE Create LICENSE Jun 3, 2019
README.md Update for kernel dim and group support - v0.1 Aug 9, 2019

README.md

Depthwise 3DConvolutions in Keras

An extension of separable convolutions for 3D volumes. Performs volumetric convolutions for each channel of the input volume and will increase the output volume based on the number of convolutional operations (denoted as depth_multiplier inside the code)

Base code for the implementation is used from: https://github.com/titu1994/MobileNetworks/blob/master/depthwise_conv.py

Requirements

  • Keras 2.2.4+
  • Tensorflow 1.13

Usage

from DepthwiseConv3D import DepthwiseConv3D

input = Input(...)

x = DepthwiseConv3D(kernel_size=(3,3,3), depth_multiplier=2)(input)
...

References:

[1] F. Chollet, Xception: Deep Learning with Depthwise Separable Convolutions [link]

You can’t perform that action at this time.