https://github.com/gengyanlei/segmentation_pytorch
semantic segmentation pytorch 语义分割
https://github.com/gengyanlei/segmentation_pytorch
deeplab-v3-plus hed hf-fcn pspnet pytorch unet
Last synced: about 1 month ago
JSON representation
semantic segmentation pytorch 语义分割
- Host: GitHub
- URL: https://github.com/gengyanlei/segmentation_pytorch
- Owner: gengyanlei
- Created: 2018-06-11T07:53:24.000Z (almost 7 years ago)
- Default Branch: master
- Last Pushed: 2021-05-10T03:43:00.000Z (almost 4 years ago)
- Last Synced: 2025-03-21T01:34:33.761Z (about 1 month ago)
- Topics: deeplab-v3-plus, hed, hf-fcn, pspnet, pytorch, unet
- Language: Python
- Homepage:
- Size: 298 KB
- Stars: 121
- Watchers: 3
- Forks: 30
- Open Issues: 5
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
## Semantic Segmentation Pytorch
```
author is leilei
Restart this project from 2017-10-01
Now the 1.alpha.0 version has been basically completed, to be tested.
TODO
Add distributed and optimize code.
```
### Environment
```
python: 3.6+
ubuntu16.04 or 18.04
pytorch 1.6 (cuda10.2 docker)
tensorboard 2.0
scikit-learn 0.24.1
```
### **Note**
+ If a black border is introduced, it will be regarded as one type, and the default is 0 !
+ label value is [1, N], 0 is black border class !
+ Not supporting distributed(NCCL), just support DataParallel.
### Getting Started
+ [How to Use](./readmes/train_cusom.md)
### Demo
+ Just see [demo.py](./demo.py)
### Evaluation index
+ Just see [metrics.py](./utils/metrics.py)
+ Support acc, mean_precision, mean_recall, mean_iou
### Support Network
- [x] [deeplab_v3_plus](models/deeplab_v3_plus.py)
- [x] [pspnet](models/pspnet.py)
- [x] [unet](models/unet.py)
- [x] [spp-net](models/spp.py)
- [x] [HF_FCN](models/hed_series/hf_fcn_vgg16.py)
- [ ] [deeplab_v3](https://github.com/pytorch/vision/blob/master/torchvision/models/segmentation/deeplabv3.py)
- [ ] [HRNet](https://github.com/HRNet/HRNet-Semantic-Segmentation/tree/pytorch-v1.1)
- [ ] [U^2Net](https://github.com/NathanUA/U-2-Net)
- [ ] ...
### Data Aug
+ [**data-augumentations**](./readmes/data_aug.md)
```
support
random zoom-in/out, random noise,
random blur, random color-jitter(brightness-contrast-saturation-hue)
random affine, random rotate, random flip
```
### Others
* [building-segmentation-dataset](https://github.com/gengyanlei/build_segmentation_dataset)
* [reflective-clothes-detect-dataset](https://github.com/gengyanlei/reflective-clothes-detect)