- Introduction
- Project Structure
- Installation
- Datasets
- Train
- Resuming training
- Test
- Results
- Reference
- Tips
This project contains the code (Note: The code is test in the environment with python=3.6, cuda=9.0, PyTorch-0.4.1, also support Pytorch-0.4.1+) for: LEDNet: A Lightweight Encoder-Decoder Network for Real-time Semantic Segmentation by Yu Wang.
├── datasets # contains all datasets for the project
| └── cityscapes # cityscapes dataset
| | └── gtCoarse # Coarse cityscapes annotation
| | └── gtFine # Fine cityscapes annotation
| | └── leftImg8bit # cityscapes training image
| └── cityscapesscripts # cityscapes dataset label convert scripts！
├── utils
| └── dataset.py # dataloader for cityscapes dataset
| └── iouEval.py # for test 'iou mean' and 'iou per class'
| └── transform.py # data preprocessing
| └── visualize.py # Visualize with visdom
| └── loss.py # loss function
├── checkpoint
| └── xxx.pth # pretrained models encoder form ImageNet
├── save
| └── xxx.pth # trained models form scratch
├── imagenet-pretrain
| └── lednet_imagenet.py #
| └── main.py #
├── train
| └── lednet.py # model definition for semantic segmentation
| └── main.py # train model scripts
├── test
| | └── dataset.py
| | └── lednet.py # model definition
| | └── lednet_no_bn.py # Remove the BN layer in model definition
| | └── eval_cityscapes_color.py # Test the results to generate RGB images
| | └── eval_cityscapes_server.py # generate result uploaded official server
| | └── eval_forward_time.py # Test model inference time
| | └── eval_iou.py
| | └── iouEval.py
| | └── transform.py
- Python 3.6.x. Recommended using Anaconda3
- Set up python environment
pip3 install -r requirements.txt
-
Env: PyTorch_0.4.1; cuda_9.0; cudnn_7.1; python_3.6,
-
Clone this repository.
git clone https://github.com/xiaoyufenfei/LEDNet.git
cd LEDNet-master
- Install Visdom.
- Install torchsummary
- Download the dataset by following the Datasets below.
- Note: For training, we currently support cityscapes , aim to add Camvid and VOC and ADE20K dataset
- You can download cityscapes from here. Note: please download leftImg8bit_trainvaltest.zip(11GB) and gtFine_trainvaltest(241MB) and gtCoarse(1.3GB).
- You can download CityscapesScripts, and convert the dataset to 19 categories. It should have this basic structure.
├── leftImg8bit
│ ├── train
│ ├── val
│ └── test
├── gtFine
│ ├── train
│ ├── val
│ └── test
├── gtCoarse
│ ├── train
│ ├── train_extra
│ └── val
-
For help on the optional arguments you can run:
python main.py -h -
By default, we assume you have downloaded the cityscapes dataset in the
./data/cityscapesdir. -
To train LEDNet using the train/main.py script the parameters listed in
main.pyas a flag or manually change them.
python main.py --savedir logs --model lednet --datadir path/root_directory/ --num-epochs xx --batch-size xx ...
- for help on the optional arguments you can run:
python main.py -h
python main.py --savedir logs --name lednet --datadir path/root_directory/ --num-epochs xx --batch-size xx --decoder --state "../save/logs/model_best_enc.pth.tar"...
- the trained models of training process can be found at here. This may not be the best one, you can train one from scratch by yourself or Fine-tuning the training decoder with model encoder pre-trained on ImageNet, For instance
more details refer ./test/README.md
- Please refer to our article for more details.
| Method | Dataset | Fine | Coarse | IoU_cla | IoU_cat | FPS |
|---|---|---|---|---|---|---|
| LEDNet | cityscapes | yes | yes | 70.6% | 87.1% | 70+ |
qualitative segmentation result examples:
If you find this code useful for your research, please use the following BibTeX entry.
@article{wang2019lednet,
title={LEDNet: A Lightweight Encoder-Decoder Network for Real-time Semantic Segmentation},
author={Wang, Yu and Zhou, Quan and Liu, Jia and Xiong，Jian and Gao, Guangwei and Wu, Xiaofu, and Latecki Jan Longin},
journal={arXiv preprint arXiv:1905.02423},
year={2019}
}
- Limited by GPU resources, the project results need to be further improved...
- It is recommended to pre-train Encoder on ImageNet and then Fine-turning Decoder part. The result will be better.