-
Notifications
You must be signed in to change notification settings - Fork 2.1k
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
Example addition for MoE #2051
base: master
Are you sure you want to change the base?
Example addition for MoE #2051
Conversation
Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA). View this failed invocation of the CLA check for more information. For the most up to date status, view the checks section at the bottom of the pull request. |
Thanks @damoonsh I will take a look at this soon. |
examples/vision/mnist_moe.py
Outdated
import numpy as np | ||
import keras | ||
from keras import layers, models | ||
import tensorflow as tf |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
From 2023 onwards all examples and guides added to Keras IO is Keras 3 only. Can you please update the implementation to Keras 3 - here is a guide for migration https://keras.io/guides/migrating_to_keras_3/
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thank you for the PR!
- why is the vocal_track_seperation.py deleted?
- Good to only have the .py file until PR approval - you can genrate the .ipynb and .md file after the .py is approved
- The example implementation needs to be in Kears 3
Not sure what happened with vocal_track file, I am trying to take it out of the PR. |
@divyashreepathihalli Took the unnecessary files out, there is only the .py file now! |
I am writing up a simple implementation for MoE for Dense and CNN model using the MNIST. Then at the end I will write an MoE class to support any kind of layer using simple approach. I have written parts of the code and will iteratively add.
Please let me know if there is a problem/concern with the example.