testing in wild and result size

[ak9250]

can you provide how to test on your own images for the celeba pretrained model and the results sizes are really small and hard to see the difference currently

[fjxmlzn]

Sorry what do you mean by "test on your own images for the celeba pretrained model"? Do you want to run InfoGAN-CR on your own image dataset, or something else?

And what do you mean by "results sizes"?

[ak9250]

@fjxmlzn I mean like testing on a single image like this one

I mean the current result grid is very small for each latent result like 32x32 for each one and you cant see it clearly

[fjxmlzn]

This is because this pre-trained model was trained on 32x32 CelebA. If you want to generate images of higher resolution, just change the training data to whatever you want and retrain the model.

[ak9250]

@fjxmlzn ok also you can test on single image instead of whole dataset?

[fjxmlzn]

This InfoGAN-CR is for generating images and is required to train on many images (same as other GANs). Sorry I don't know what you mean by "test on single image". Could you please clarify more on that?

Do you mean changing the factors of a single given image?