NiftyNet Files

An open-source convolutional neural networks platform for research

This is an exact mirror of the NiftyNet project, hosted at https://github.com/NifTK/NiftyNet. SourceForge is not affiliated with NiftyNet. For more information, see the SourceForge Open Source Mirror Directory.

The interactive file manager requires Javascript. Please enable it or use sftp or scp.
You may still browse the files here.

Name	Modified	Size	InfoDownloads / Week
Parent folder
0.4.0.tar.gz	2018-09-13	2.7 MB	0
0.4.0.zip	2018-09-13	2.9 MB	0
README.md	2018-09-13	1.2 kB	0
Totals: 3 Items		5.5 MB	0

Added

niftynet.layer: new layers
- Tversky loss function for image segmentation
- Random affine augmentation layer
- Random bias field augmentation layer
- Group normalisation layer
- Squeeze and excitation blocks
Documentation
Misc.
- Subject id from filename with regular expression
- Versioning with python-versioneer
- Tested with TensorFlow 1.10

Changed

niftynet.engine: improved core functions
- IO modules based on tf.data.Dataset (breaking changes)
- Decoupled the engine and event handlers
Migrated the code repository, model zoo, and niftynet.io source code to github.com/niftk.

Source: README.md, updated 2018-09-13

Other Useful Business Software

Our Free Plans just got better! | Auth0 Icon

Our Free Plans just got better! | Auth0

With up to 25k MAUs and unlimited Okta connections, our Free Plan lets you focus on what you do best—building great apps.

You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.

Try free now

Deliver trusted data with dbt Icon

Deliver trusted data with dbt

dbt Labs empowers data teams to build reliable, governed data pipelines—accelerating analytics and AI initiatives with speed and confidence.

Data teams use dbt to codify business logic and make it accessible to the entire organization—for use in reporting, ML modeling, and operational workflows.

Learn More

Recommended Projects

GIMP ML
AI for GNU Image Manipulation Program
waifu2x
Single-image super-resolution for anime-style art
MedGemma
Collection of Gemma 3 variants that are trained for performance
Image Super-Resolution (ISR)
Super-scale your images and run experiments with Residual Dense
AnimeGAN
A simple PyTorch Implementation of Generative Adversarial Networks