this is a demo
2023.5.28: The BG-Net model has been optimised. The paper will be updated later.
- PyTorch 1.x or 0.41
- Create an anaconda environment.
conda create -n=<env_name> python=3.6 anaconda
conda activate <env_name>- Install PyTorch.
conda install pytorch torchvision cudatoolkit=10.1 -c pytorch- Install pip packages.
pip install -r requirements.txtTraining on 2018 Data Science Bowl dataset
- Download dataset from here to inputs/ and unzip. The file structure is the following:
inputs
└── ISIC2018
├── images
├──ISIC_00000001.png
├──ISIC_00000002.png
├──ISIC_0000000n.png
├── masks
├──ISIC_00000001.png
├──ISIC_00000002.png
├──ISIC_0000000n.png
...
2. Train the model.
```sh
python train.py --dataset ISIC2018 --arch BG-Net
- Evaluate.
python text.py --name ISIC2018-model
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent