a question

[mikeyjhom]

Dear Mr. Tal Daniel
I apologize for taking up your time. I have a question and would like to request your help. I trained the soft-intro_vae model using the code you provided, and the image generated during the training process was very good. However, after the model training was completed, I used the trained model to generate images, but received strange results
This is the image generated during the training process

This is the image generated by calling the trained model

Is the method I used to call the trained model incorrect?
Think about seeking your advice on a solution. I hope to receive your help. Thank you very much

[taldatech]

Hmmmm I think it has to do with Batch Normalization. I assume you use the standard architecture (and not the style-based one). Try turning BatchNorm on/off (model.train()/model.eval()) and see how it affects the results. The architecture in this model is very out-dated. I would replace all the Batch Normalization with Group Normalization to avoid depending on the batch size statistics.

[mikeyjhom]

Okay, thank you very much for your reply. I will try to solve the problem based on your suggestions