You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The desired PR addressing this issue should include:
Implementation of activation class named as MishActivation (you can take inspiration from the implementation of HardSigmoid as reference) added to the Activations.kt file
Documentation of activation function
JUnit tests in api module
Support for export of activation function to JSON (see ModelSaver.kt)
Support for import of activation function from JSON (see ModelLoader.kt)
P.S. If you want to take this ticket, please leave the comment below
P.P.S Read the Contributing Guidelines.
Hi, @digantamisra98! Please leave a comment here to assign this ticket to you.
As I understand, you are the author of the Mish paper, a really great paper and results!
@zaleslaw Yes, I am taking this up and will be happy to add others over the weekend (hopefully). Thank you for your compliment and willingness to add it in the library :)
@digantamisra98 I hope that KotlinDL could be more open to DL innovations than Keras with huge codebase and be faster in implementation of new ideas, will wait review request from you.
The Mish activation function is missed in KotlinDL.
Read more about Mish: A Self Regularized Non-Monotonic Neural Activation Function
The desired PR addressing this issue should include:
MishActivation
(you can take inspiration from the implementation ofHardSigmoid
as reference) added to theActivations.kt
fileapi
moduleP.S. If you want to take this ticket, please leave the comment below
P.P.S Read the Contributing Guidelines.
The reference implementation could be taken from tensorflow-addons
The text was updated successfully, but these errors were encountered: