lxp
f32016e467
模型训练
|
1 maand geleden | |
|---|---|---|
| network | 7 jaren geleden | |
| pretrained_model | 7 jaren geleden | |
| src | 7 jaren geleden | |
| test_img | 7 jaren geleden | |
| test_output | 6 jaren geleden | |
| .gitignore | 7 jaren geleden | |
| LICENSE | 4 jaren geleden | |
| README.md | 6 jaren geleden | |
| python算法时长计算研究生版.py | 2 maanden geleden | |
| test.lua | 7 jaren geleden | |
| test.py | 6 jaren geleden | |
| train_corrector.py | 1 maand geleden | |
| 参考.py | 1 maand geleden | |
| 模型调用.py | 1 maand geleden | |
| 焦炭计算公式.py | 1 maand geleden | |
| 煤矿途径地点初始温度代码接收java数据算法.py | 2 maanden geleden | |
| 解冻库python代码接收java算法数据.py | 2 maanden geleden |
README.md
CartoonGAN-Test-Pytorch-Torch
Pytorch and Torch testing code of CartoonGAN [Chen et al., CVPR18]. With the released pretrained models by the authors, I made these simple scripts for a quick test.
Getting started
- Linux
- NVIDIA GPU
- Pytorch 0.3
Torch
git clone https://github.com/Yijunmaverick/CartoonGAN-Test-Pytorch-Torch cd CartoonGAN-Test-Pytorch-Torch
Pytorch
The original pretrained models are Torch nngraph models, which cannot be loaded in Pytorch through load_lua. So I manually copy the weights (bias) layer by layer and convert them to .pth models.
Download the converted models:
sh pretrained_model/download_pth.shFor testing:
python test.py --input_dir YourImgDir --style Hosoda --gpu 0
Torch
Working with the original models in Torch is also fine. I just convert the weights (bias) in their models from CudaTensor to FloatTensor so that cudnn is not required for loading models.
Download the converted models:
sh pretrained_model/download_t7.shFor testing:
th test.lua -input_dir YourImgDir -style Hosoda -gpu 0
Examples (Left: input, Right: output)
Note
- The training code should be similar to the popular GAN-based image-translation frameworks and thus is not included here.
Acknowledgement
Many thanks to the authors for this cool work.
Part of the codes are borrowed from DCGAN, TextureNet, AdaIN and CycleGAN.