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

ENH: Bayesian neural network architectures with training requisites #126

Merged
merged 46 commits into from
Jun 19, 2021

Conversation

Aakanksha-Rana
Copy link
Member

@Aakanksha-Rana Aakanksha-Rana commented Mar 22, 2021

Types of changes

  • Bug fix (non-breaking change which fixes an issue)
  • [ x] New feature (non-breaking change which adds functionality)
  • Breaking change (fix or feature that would cause existing functionality to change)

Summary

Checklist

  • All tests passing
  • I have added tests to cover my changes
  • I have updated documentation (if necessary)
  • My code follows the code style of this project
    (we are using black: you can pip install pre-commit,
    run pre-commit install in the pydra directory
    and black will be run automatically with each commit)

Acknowledgment

  • I acknowledge that this contribution will be available under the Apache 2 license.

@Aakanksha-Rana Aakanksha-Rana changed the title [WIP] Bayesian Neural Network Training (Meshnet + UNet) [WIP] Bayesian Neural Network Architectures with training requisites Mar 23, 2021
@Aakanksha-Rana Aakanksha-Rana changed the title [WIP] Bayesian Neural Network Architectures with training requisites [WIP] bayesian neural network architectures with training requisites Mar 23, 2021
@satra
Copy link
Contributor

satra commented Mar 25, 2021

please add some tests, to make sure the code does what it should do. this is not realistic training, but just to exercise the code on some dummy but predefined data.

@Aakanksha-Rana
Copy link
Member Author

Thanks. I will add them.

@Aakanksha-Rana
Copy link
Member Author

Adding new architectures. Tests will be added soon for all of them.

@Aakanksha-Rana
Copy link
Member Author

Bayesian Training is updated now with tests.

@Aakanksha-Rana Aakanksha-Rana changed the title [WIP] bayesian neural network architectures with training requisites Bayesian neural network architectures with training requisites Jun 19, 2021
nobrainer/models/asdnet.py Outdated Show resolved Hide resolved
nobrainer/models/vnet.py Outdated Show resolved Hide resolved

def vnet(
n_classes=1,
input_shape=(256, 256, 256, 1),
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@Aakanksha-Rana - does this actually work at this resolution?

@satra satra changed the title Bayesian neural network architectures with training requisites ENH: Bayesian neural network architectures with training requisites Jun 19, 2021
@satra satra merged commit 42620da into neuronets:master Jun 19, 2021
@Aakanksha-Rana
Copy link
Member Author

Fixes #104

@Aakanksha-Rana
Copy link
Member Author

Fixes #107

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

Successfully merging this pull request may close these issues.

2 participants