Skip to content
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

Error in overlay_y_on_x #20

Open
PF-Maillard opened this issue Jun 21, 2024 · 0 comments
Open

Error in overlay_y_on_x #20

PF-Maillard opened this issue Jun 21, 2024 · 0 comments

Comments

@PF-Maillard
Copy link

Hello,

I wrote a code using your project but encountered an error where considering a set of two entries X, the result of MyNet.predict(X) and MyNet.predict(X[0:1]) gives different results for the first element.

After investigation, it sees that overlay_y_on_x considers x.max() to define a label. However, if x is a unique tensor or x is a set of tensor, the result will be different (considering the max of all of the tensors). This error leads to different predictions for x if considered in a set of tensors or a unique tensor. I guess it is possible to solve it by replacing x.max to 1 or to iterate over all the tensor to get the max of each of them.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant