lilili666-hit

thank you very much. I have another question for you, why G_ Does loss have a negative value? After a period of time, it will output a negative value and...

Hi Yi Wang ,Can you share the place2 pretrained model ，thank you very much。

when i was testing ，i have met another problem. ValueError: Dimension 3 in both shapes must be equal, but are 256 and 1024. Shapes are [3,3,64,256] and [3,3,64,1024]. for 'Assign_30'...

 this is my training detail 。thank you very much！

The picture size of place2 is 256 * 256. How do you use 256 * 512 for training? Do you directly change the fractional rate of 256 * 256 pictures...

Can this program be fine-tuned? For example, import a pre-trained model, then freeze certain layers and then train.

Can you give me an example? thank you very much.

Hi Yi Wang. What applications do you think this technology has in real life? For example, what kind of practical problems can be solved?

I am training from the newly selected data set. To what extent can the first stage of training be identified as convergence？thanks for your help

 Is the loss function image of this discriminator normal? I trained from scratch with a newly selected dataset.