Open ly15681910119 opened 2 years ago
When the program trains the CVAE, the program reports an error:
computing log_prob at site 'y'
The main problem is this line of code:
loss = svi.step(inputs, outputs) / inputs.size(0)
me too! A same problems with you!
Hey guys... this smells like a compatibility issue. Pyro is in active development. When I created this example as a contribution to them, I used Pyro's 1.4.x; Pyro is now over 1.8. Let me investigate and come back to you.. Cheers!
Hey guys... this smells like a compatibility issue. Pyro is in active development. When I created this example as a contribution to them, I used Pyro's 1.4.x; Pyro is now over 1.8. Let me investigate and come back to you.. Cheers!
Thank you!
I have the same problem, is there a solution now?
I have the same problem, is there a solution now?
set validate_args=False
in pyro.sample('y', dist.Bernoulli(mask_loc, validate_args=False).to_event(1), obs=mask_ys)
. It seems work.
When the program trains the CVAE, the program reports an error:
The main problem is this line of code: