Dose anyone can give an example of FCN using keras?

[meanmee]

I just have some trouble in using ConVNet for semantic Segmentation. Since I am not sure about how to create the data(like feeding the Pascal VOC data to the Segmentation model coded by Keras ) and the loss function.
reference: https://gist.github.com/longjon/16db1e4ad3afc2614067#file-readme-md

[lukovkin]

We are working on Undecimated FCN for sequences, inspired by paper (arXiv:1508.00317v1 [
stat.ML]), which is based on works on Semantic Segmentation.
Work is in progress, repo is here - https://github.com/lukovkin/ufcnn-keras.
Our subject is a bit different, so we saw the model you mentioned, but not going to reproduce it exactly.

[liuy2c]

Could you share me a FCN Source code by keras for me. Thank u very much. My email is "liuy2c@163.com"

[ahundt]

@meanmee @moo169
These items & repositories are also relevant to FCN:

• official keras-contrib repository which is the upstream source for Keras, and has a DensenetFCN implementation
• additional datasets - coco + voc2012 keras-contrib#47 incorporating coco + voc 2012
• segmentation and FCN training examples + class keras-contrib#59 dealing with gaps in FCN training performance
• DenseNetFCN not training to expected performance keras-contrib#63 training on other FCN networks
• Keras-FCN, which I was planning to adapt for a merge into keras-contrib also has a SegDataGenerator implementation with some of the features you are looking for in your comments, plus additional models and experimental support for coco.
• https://github.com/0bserver07/One-Hundred-Layers-Tiramisu

[stale]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed after 30 days if no further activity occurs, but feel free to re-open a closed issue if needed.