# BSGAN

**Repository Path**: renfh/bsgan

## Basic Information

- **Project Name**: BSGAN
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2024-09-29
- **Last Updated**: 2024-11-09

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# BSGAN：Facial Attribute Editing via Style Disentanglement

#### Requirement

```
python=3.6.6
conda install -y pytorch=1.0.1 torchvision=0.2.2  cudatoolkit=10.1 -c pytorch
pip install pillow tqdm tensorboardx pyyaml
```


#### Download the dataset.

We recommend you to download CelebA-HQ from [CelebAMask-HQ](http://github.com/switchablenorms/CelebAMask-HQ). Anyway you shound get the dataset folder like:
```
celeba_or_celebahq
 - img_dir
   - img0
   - img1
   - ...
 - train_label.txt
```


#### Train

```
python core/train.py --config configs/celeba-hq_256.yaml --gpus 0
```


#### Test

```
python core/test.py --config configs/celeba-hq_256.yaml --checkpoint $your_checkpoint --input_path $your_input_path --output_path results
```


#### Acknowledgments

This source code is inspired by HiSD，StyleGAN2，SimAM, and L2m-gan.