https://github.com/lusinlu/epe-module
[ICIP2022] Entropy guided feature extraction for real time semantic segmentation
https://github.com/lusinlu/epe-module
artificial-intelligence machine-learning mobile-networks mobilenet pytorch pytorch-implementation real-time-semantic-segmentation semantic-segmentation
Last synced: 3 months ago
JSON representation
[ICIP2022] Entropy guided feature extraction for real time semantic segmentation
- Host: GitHub
- URL: https://github.com/lusinlu/epe-module
- Owner: lusinlu
- Created: 2021-09-15T11:39:37.000Z (over 3 years ago)
- Default Branch: main
- Last Pushed: 2022-07-11T11:59:49.000Z (almost 3 years ago)
- Last Synced: 2024-12-30T11:29:15.114Z (5 months ago)
- Topics: artificial-intelligence, machine-learning, mobile-networks, mobilenet, pytorch, pytorch-implementation, real-time-semantic-segmentation, semantic-segmentation
- Language: Python
- Homepage:
- Size: 1.38 MB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# EPE Module
[ICIP 2022] Official implementation of the [paper](https://arxiv.org/abs/2207.03233) "Entropy-Based Feature Extraction For Real-Time Semantic Segmentation".
## Usage (test)
Pretrained RTEffNet+EPE model is available from [Google Drive](https://drive.google.com/file/d/12H8WmfGOX4cZ9jeFPAo6aHU7LzD7HtBE/view?usp=sharing). For the testing of the model using the Cityscapes validation set run the following command:
`python test.py --data_path path/to/validation/set --cuda --weights path/to/downloaded/weight `
## Usage (train)
To train the RTEffNet+EPE module on Cityscapes dataset run the following command:
` python main.py --dataset cityscapes --data_path ../../datasets/cityscapes/ --cuda`
## Architecture
## Citation
If you find the code useful for your research, please consider citing our works
```
@article{abrahamyanepe,
title={Entropy-Based Feature Extraction For Real-Time Semantic Segmentation},
author={Lusine, Abrahamyan and Nikos, Deligiannis},
journal={Proceedings of the IEEE International Conference on Image Processing (ICIP)},
publisher = {IEEE},
year={2022}
}
```
## Acknowledgement
Code for EfficientNet is borrowed from [EfficientNet-PyTorch](https://github.com/lukemelas/EfficientNet-PyTorch) and for the Cityscapes loader from [TORCHVISION.DATASETS](https://pytorch.org/vision/0.8/datasets.html) and [pytorch-semantic-segmentation](https://github.com/zijundeng/pytorch-semantic-segmentation).