This repository is tensorFlow implementation of LinkNet: Exploiting Encoder Representations for Efficient Semantic Segmentation (https://arxiv.org/abs/1707.03718) and the official Torch implementation (https://github.com/e-lab/LinkNet) and the pytorch implementation by PavlosMelissinos (https://github.com/e-lab/pytorch-linknet), trained on the Cityscapes dataset (https://www.cityscapes-dataset.com/).
- The video of results (logs/results/cityscapes_stuttgart_02_pred.avi):
- Python 3.5 or greater
- Tensorflow 1.3 or greater
- OpenCV3
Linknet_model.py:
- bulid the Linknet model.
load_cityscapes_data.py:
- preprocess dataset and generate train/val batch data. that all Cityscapes training (validation) image directories have been placed in data_dir/cityscapes/leftImg8bit/train (data_dir/cityscapes/leftImg8bit/val) and that all corresponding ground truth directories have been placed in data_dir/cityscapes/gtFine/train (data_dir/cityscapes/gtFine/val).
train_linknet.py:
- train linknet class
demo.py:
- run a model checkpoint on all frames in a Cityscapes demo sequence directory and creates a video of the result.
This software is released under a creative commons license which allows for personal and research use only. For a commercial license please contact the authors. You can view a license summary here: http://creativecommons.org/licenses/by-nc/4.0/