zhangzc21/exsingan

ExSinGAN

Code for the paper: "ExSinGAN: learning an explainable Generative Model from a Single Image (BMVC 2021)"

code

Our code refered to the following projects:

• SinGAN: https://github.com/tamarott/SinGAN
• DGP: https://github.com/XingangPan/deep-generative-prior

And we rewrited the SinGAN and DGP for more concise expression.

Download pre-trained models

Please download Pretrained VGG and BigGAN from Google drive, and put them to Pretrained folder.

Install dependencies

pip install -r requirements.txt

Train

To train ExSinGAN, just running

python main_train.py --input_dir <input_dir> --input_name <image>

e.g., if you has an image leaningtower.jpg in Input/Images, just run

python main_train.py --input_dir Input/Images --input_name leaningtower.jpg

For more details of parameters, please see Models/config.py

We also offered a script To train SinGAN, just running

python main_train.py --input_dir <input_dir> --input_name <image> --use_struct False --use_semantic False --rescale_method singan --pyramid_height None

Random samples

Once the model is trained completely, the syntheses are stored in the Output directory. You can sample more syntheses by running

python random_samples.py --model_path <model_path> --num <num>

exsingan's Issues

Code bug

Thanks for your excellent work , I trying to run your code. But I get a bug in your code
https://github.com/zhangzc21/ExSinGAN/blob/main/Models/ExSinGAN.py#L488

Bug detail: AttributeError: 'Namespace' object has no attribute 'alpha'

It seems that opt doesn't have alpha , maybe other name? like alpha_dip, etc.

Have a good day~

A question

Hello, thank you so much for your code.
I want to know if I want to batch generate random samples with a resolution of 1084*1084, how do I adjust the parameters of the code to achieve this.

A question about three features

I'm confused about these three features from your paper. How did you divide them from one picture. Can you introduce some papers about three features? Thank you.