-
Notifications
You must be signed in to change notification settings - Fork 19
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
Inverse temperature #10
Comments
Many thanks for your implementation. It works well. Am I right? |
Hi @YaserGholizade, the fully connected layer is treated as the final value on each leaf node. You can see its dimension (code here) is |
Thanks @xuyxu According to the main paper, for MNIST classification, each leaf should has ten values (a probability vector). There is not any fully connected layer. But in your code, you assigned the path probability to each leaf |
The algorithm here is same as that in the raw paper, despite that we use matrices for faster computation. Instead of computing path probabilities one by one, which is very slow, |
Hello, In the original article, they say "In order to avoid very soft decisions in the tree, we introduced an inverse
temperature β to the filter activations prior to calculating the sigmoid." I am not sure, but I think you did not implement this temperature, did you?. Thanks!
The text was updated successfully, but these errors were encountered: