cc

The loss is going to 'nan' when i load the correct ckpt, do you have this problem? I trained on VAS dataset.

The pretrained models of stable diffusion could be downloaded from [https://huggingface.co/CompVis/stable-diffusion-v1-4](https://huggingface.co/CompVis/stable-diffusion-v1-4/)

I've got the same problem. And I extracted train_loc and val_loc from trainval_loc according to "trainclasses.txt" and "valclasses.txt". But the result is not so good, especially at test_seen.

The 'gzsl unseen' is 34. while it is 39.3 in the paper. And the 'gzsl seen' is only 26. while it is 66.7 in the paper. The classifier is knn...

Hello, may I ask whitch dataset you did used? I have downloaded the dataset but there is no train_loc and val_loc in the proposed split, and then I extract them...

@lerndeep 1. you can extract train_loc and val_loc accrording to the trainclasses.txt and valclasses.txt. python code: `def load_data(att_path, res_path, val_size, trainval_split=1): """ :param val_size: if there is no train_loc and...

Hi, I got the same problem, have you solved it?

You may check it again and I found the .bin files: 

I modified the `load_model_from_config` function in 'txt2img.py':  and solve the problem, you can try it.