Shuyang Gu

1. The path/to/dataset should point to the folder contains raw images like jpg or png, similar to pytorch-fid code (https://github.com/mseitzer/pytorch-fid) in the reference. 2. Yes, the activation files generated automatically...

> Thank you > I tried to run the Extract features" > where i put your city.rar, in the path/to/dataset， but in the runtime prompt "“IsADirectoryError: [Errno 21] Is a ...

> Thank you for your help, but one problem I encountered during debugging “Extract features”is > “ File "GIQA-master/write_act.py", line 67, in get_activations >     images = images.transpose((0, 3, 1, 2))...

> Thank you for your reply！ > So, I would like to ask, are all the photos in your dataset color images?Are there any restrictions on image data sets? Only...

If your images are not in the same size, you need to resize them to the same size, then the error will be fixed.

> If your images are not in the same size, you need to resize them to the same size, then the error will be fixed. And also, for building GMM...

It's inspired by multinomail_diffusion(https://github.com/ehoogeboom/multinomial_diffusion). log scale could make the computation more stable. You may refer to their code and paper for more details.

The PCA model do compress the information from 2048 channel to 774 channel, you may check if there's something wrong in the PCA model, or maybe your package version is...

Thanks for the great work, I wonder is there any update on the new code?

I meet the same problem, i think there might be something wrong when loading the g_optimizer and d_optimizer.