-
Notifications
You must be signed in to change notification settings - Fork 33
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
BNN broadcastable error #28
Comments
Hi! I think the issue is that you're giving your Categorical likelihood an event dim, if I remember correctly it should automatically account for the classes on the trailing dimension. Try changing to
Hope that solves it! Otherwise I will have to have another look at this in more detail. |
Hi,
|
Are your target variables one-hot encoded? They need to be label encoded, i.e. 0, 1, 2, 3 for your four classes. |
yes, my target variables are one-hot encoded. Below is an example of my tensor target labels and I have given batch_size = 8 in dataloader.
|
Hi,
I would be really glad if I could get some help. Thank you!
I am using Tyxe: Pyro model, according to which I have converted the fc layer to probabilistic layer. I am facing the broadcastable error :
I am using the categorical likelihood!
Below I have added my model for reference:
The text was updated successfully, but these errors were encountered: