English | 简体中文
This project aims at providing a concise, easy-to-use, modifiable reference implementation for semantic segmentation models using PyTorch.
# semantic-segmentation-pytorch dependencies pip install ninja tqdm # follow PyTorch installation in https://pytorch.org/get-started/locally/ conda install pytorch torchvision -c pytorch # install PyTorch Segmentation git clone https://github.com/Tramac/awesome-semantic-segmentation-pytorch.git - Single GPU training
# for example, train fcn32_vgg16_pascal_voc: python train.py --model fcn32s --backbone vgg16 --dataset pascal_voc --lr 0.0001 --epochs 50 - Multi-GPU training
# for example, train fcn32_vgg16_pascal_voc with 4 GPUs: export NGPUS=4 python -m torch.distributed.launch --nproc_per_node=$NGPUS train.py --model fcn32s --backbone vgg16 --dataset pascal_voc --lr 0.0001 --epochs 50 - Single GPU evaluating
# for example, evaluate fcn32_vgg16_pascal_voc python eval.py --model fcn32s --backbone vgg16 --dataset pascal_voc - Multi-GPU evaluating
# for example, evaluate fcn32_vgg16_pascal_voc with 4 GPUs: export NGPUS=4 python -m torch.distributed.launch --nproc_per_node=$NGPUS eval.py --model fcn32s --backbone vgg16 --dataset pascal_voc cd ./scripts #for new users: python demo.py --model fcn32s_vgg16_voc --input-pic ../tests/test_img.jpg #you should add 'test.jpg' by yourself python demo.py --model fcn32s_vgg16_voc --input-pic ../datasets/test.jpg .{SEG_ROOT} ├── scripts │ ├── demo.py │ ├── eval.py │ └── train.py - FCN
- ENet
- PSPNet
- ICNet
- DeepLabv3
- DeepLabv3+
- DenseASPP
- EncNet
- BiSeNet
- PSANet
- DANet
- OCNet
- CGNet
- ESPNetv2
- DUNet(DUpsampling)
- FastFCN(JPU)
- LEDNet
- Fast-SCNN
- LightSeg
- DFANet
DETAILS for model & backbone.
.{SEG_ROOT} ├── core │ ├── models │ │ ├── bisenet.py │ │ ├── danet.py │ │ ├── deeplabv3.py │ │ ├── deeplabv3+.py │ │ ├── denseaspp.py │ │ ├── dunet.py │ │ ├── encnet.py │ │ ├── fcn.py │ │ ├── pspnet.py │ │ ├── icnet.py │ │ ├── enet.py │ │ ├── ocnet.py │ │ ├── psanet.py │ │ ├── cgnet.py │ │ ├── espnet.py │ │ ├── lednet.py │ │ ├── dfanet.py │ │ ├── ...... You can run script to download dataset, such as:
cd ./core/data/downloader python ade20k.py --download-dir ../datasets/ade | Dataset | training set | validation set | testing set |
|---|---|---|---|
| VOC2012 | 1464 | 1449 | ✘ |
| VOCAug | 11355 | 2857 | ✘ |
| ADK20K | 20210 | 2000 | ✘ |
| Cityscapes | 2975 | 500 | ✘ |
| COCO | |||
| SBU-shadow | 4085 | 638 | ✘ |
| LIP(Look into Person) | 30462 | 10000 | 10000 |
.{SEG_ROOT} ├── core │ ├── data │ │ ├── dataloader │ │ │ ├── ade.py │ │ │ ├── cityscapes.py │ │ │ ├── mscoco.py │ │ │ ├── pascal_aug.py │ │ │ ├── pascal_voc.py │ │ │ ├── sbu_shadow.py │ │ └── downloader │ │ ├── ade20k.py │ │ ├── cityscapes.py │ │ ├── mscoco.py │ │ ├── pascal_voc.py │ │ └── sbu_shadow.py - PASCAL VOC 2012
| Methods | Backbone | TrainSet | EvalSet | crops_size | epochs | JPU | Mean IoU | pixAcc |
|---|---|---|---|---|---|---|---|---|
| FCN32s | vgg16 | train | val | 480 | 60 | ✘ | 47.50 | 85.39 |
| FCN16s | vgg16 | train | val | 480 | 60 | ✘ | 49.16 | 85.98 |
| FCN8s | vgg16 | train | val | 480 | 60 | ✘ | 48.87 | 85.02 |
| FCN32s | resnet50 | train | val | 480 | 50 | ✘ | 54.60 | 88.57 |
| PSPNet | resnet50 | train | val | 480 | 60 | ✘ | 63.44 | 89.78 |
| DeepLabv3 | resnet50 | train | val | 480 | 60 | ✘ | 60.15 | 88.36 |
Note: lr=1e-4, batch_size=4, epochs=80.
See TEST for details.
.{SEG_ROOT} ├── tests │ └── test_model.py - add train script
- remove syncbn
- train & evaluate
- test distributed training
- fix syncbn (Why SyncBN?)
- add distributed (How DIST?)