MarkCunningham0410 / Gated-SCNN

Tensorflow implementation of Gated Shape CNNs

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Gated Shape CNNs

Implementation of this paper for semantic segmentation. Written using tensorflow 2.0, and the model is implemented as a subclassed tf.keras.Model.

There are some differences between this implementation and the paper:

  • Use normal resnet instead of wide resnet
  • Use generalised dice loss instead of cross entropy for the edge segmentation

IOU

At the moment the best model I have trained is much worse than the paper, but this was because I did not replace the final downsampling layers in the resnet with atrous convolutions. I have done this now, but need to get access to a bunch of gpus to train on a decent batch size.

Implementation road sidewalk building wall fence pole traffic light traffic sign vegetation terrain sky person rider car truck bus train motorcycle bicycle
Paper 98.3 86.3 93.3 55.8 64 70.8 75.9 83.1 93 65.1 95.2 85.3 67.9 96 80.8 91.2 83.3 69.6 80.4
This repo 95.4 72.3 86.5 49.1 49 40.6 40.7 56.9 87.7 53.4 89 70.5 52.8 90.1 71.9 76.5 58.7 50 63.8

Todo

  • Train better model on multiple gpus

About

Tensorflow implementation of Gated Shape CNNs


Languages

Language:Python 100.0%