# Implementing Fully Convolutional Networks (FCNs) from scratch in Keras and

**URL:** <https://discuss.ai.google.dev/t/implementing-fully-convolutional-networks-fcns-from-scratch-in-keras-and/15381>\
**Category:** Show and Tell\
**Tags:** education, keras\
**Created:** [December 19, 2022, 7:07am UTC](https://discuss.ai.google.dev/t/implementing-fully-convolutional-networks-fcns-from-scratch-in-keras-and/15381 "2022-12-19T07:07:09Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![MWITIDERRICK](https://d1dlmcr85iqnpo.cloudfront.net/user_avatar/discuss.ai.google.dev/mwitiderrick/32/93_2.png) [@MWITIDERRICK](https://discuss.ai.google.dev/u/MWITIDERRICK)\
**Post date:** [December 19, 2022, 7:07am UTC](https://discuss.ai.google.dev/t/implementing-fully-convolutional-networks-fcns-from-scratch-in-keras-and/15381/1 "2022-12-19T07:07:09Z")

</div>

> **[Implementing Fully Convolutional Networks (FCNs) from scratch in Keras and...](https://www.machinelearningnuggets.com/implementing-fully-convolutional-networks-fcns-from-scratch-in-keras-and-tensorflow/)**
>
> In 2014, Jonathan Long, Evan Shelhamer, and Trevor Darrell proposed solving image segmentation problems using Fully Convolutional Neural Networks(FCNs). FCNs have no fully connected layers.
> 
> Image segmentation involves making a prediction for each...