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

Add support for multiple loss functions #3

Open
Chronocook opened this issue Sep 10, 2018 · 3 comments
Open

Add support for multiple loss functions #3

Chronocook opened this issue Sep 10, 2018 · 3 comments

Comments

@Chronocook
Copy link
Collaborator

No description provided.

@Chronocook
Copy link
Collaborator Author

I think it is just set to MAE right now, this should be more explicit as it's super important to learn

@SharathGa
Copy link
Contributor

@Chronocook I am interested to work on this . I am planning to add the following initally-

  • Binary cross entropy :- Binary classification.
  • categorical cross entropy loss :- Multiclass classification.

@SharathGa
Copy link
Contributor

@Chronocook
#3 As part of Hacktober,

From line 186 to line 230 we have to fix the error.

Creating a class for the loss functions with parameter (target, prediction) :
including the mae, rmse, binary cross entropy and categorical cross entropy.

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

No branches or pull requests

2 participants