You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I am trying to train this model on a new dataset. I noticed that the prompt in stage2 said "the teacher can be any sgan3 pretrained model, e.g. from the stylegan3 official repository also works", so I downloaded the stylegan3 pre-training model on NVIDIA catalog(https://catalog.ngc.nvidia.com/orgs/nvidia/teams/research/models/stylegan3), but when it was used as the stage2 teacher, an error was reported that the size of the Tensor did not match, I want to know why this error occurred? Am I got it wrong?
Sorry to take up your time. I'm looking forward to your reply.
The text was updated successfully, but these errors were encountered:
eastwind123
changed the title
some questions in training
Some questions on training
Feb 20, 2023
I believe the downloaded model expects resolution 512 instead of 256.
I also tried it, but the size of the Tensor still doesn't match. The error is “The size of tensor a (24) must match the size of tensor b (12) at non-singleton dimension 0”.
I think specifically for that model you might need to change the cbase parameter using --cbase=16384 (and maybe also --cmax=512) to match the number of channel dimensions.
I am trying to train this model on a new dataset. I noticed that the prompt in stage2 said "the teacher can be any sgan3 pretrained model, e.g. from the stylegan3 official repository also works", so I downloaded the stylegan3 pre-training model on NVIDIA catalog(https://catalog.ngc.nvidia.com/orgs/nvidia/teams/research/models/stylegan3), but when it was used as the stage2 teacher, an error was reported that the size of the Tensor did not match, I want to know why this error occurred? Am I got it wrong?
![LI2F)U $ @5GBEO)C7UMWXH](https://user-images.githubusercontent.com/57025825/220122071-134e4116-f00f-42f4-86e7-a58fd221547c.png)
Sorry to take up your time. I'm looking forward to your reply.
The text was updated successfully, but these errors were encountered: