Keras implementation of Real-Time Semantic Segmentation on High-Resolution Images
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
output Reordered stuff, changed test script Dec 5, 2017
LICENSE Create LICENSE Jan 24, 2018
README.md Update README.md Dec 5, 2017
model.py Better checkpointing, faster data augmentation Dec 5, 2017
test quick fix Dec 5, 2017
train quick fix Dec 5, 2017
utils.py Better checkpointing, faster data augmentation Dec 5, 2017

README.md

Keras-ICNet

[paper]

Keras implementation of Real-Time Semantic Segmentation on High-Resolution Images. Training in progress!

Requisites

  • Python 3.6.3
  • Keras 2.1.1 with Tensorflow backend
  • A dataset, such as Cityscapes or Mapillary (Mapillary was used in this case).

Train

Issue ./train --help for options to start a training session, default arguments should work out-of-the-box.

You need to place the dataset following the next directory convention:

.
├── mapillary                   
|   ├── training
|   |   ├── images             # Contains the input images
|   |   └── instances          # Contains the target labels
|   ├── validation
|   |   ├── images
|   |   └── instances
|   └── testing
|   |   └── images

These are the results of training for 300 epochs ./train --epochs 300

Training

conv6_cls_categorical_accuracy conv6_cls_loss loss

Validation

val_conv6_cls_categorical_accuracy val_conv6_cls_loss val_loss

Test

Issue ./test --help for options to start a testing session, default arguments should work out-of-the-box.

Output examples

10 07

TODO

  • Perform class weighting