Closed jiahaolu97 closed 2 years ago
Problem solved.
Using a too-small diffusion_steps
will cause the error. When I set diffusion_steps=10
, the betas
will not pass assertion.
Using a recommend diffusion_steps = 1000
will not cause the problem.
I'm closing this issue.
@RoyLJH Hello, do you need to make any adjustments when using your own data set code part when training guided_classifier?
When I use the recommended command
There seems to be an assertion error
And I print the betas value :
How to solve this bug?