An agnostic algorithm for bipartitioning of feature maps. Really fast, even for high resolutions.
Project description
fastncut
A Fast Algorithm for Normalized Cut with Applications on Bipartitioning Feature Maps in Deep Learning
A fast agnostic algorithm for bipartitioning images or feature maps.
Implemented in Pytorch.
Really cool!
The ingenious idea of Shi & Malik was brought into practice.
See https://github.com/andylucny/fastncut
26.3.2026, 2.0.4, initial release on PyPY with documentation
2.4.2026, 2.0.5, support of data formats nc and bnc
3.4.2026, 2.0.6, support of masks for data formats nc and bnc
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file fastncut-2.0.6.tar.gz.
File metadata
- Download URL: fastncut-2.0.6.tar.gz
- Upload date:
- Size: 7.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.13
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
970d8a6d9da6bf6fbccdc1ac224245437110c353eadb444953838c0fd4426d16
|
|
| MD5 |
e9996db9fd1030086e547808248910d9
|
|
| BLAKE2b-256 |
843da08378c3e2fe10ee909266ffe9e76a94c8d55264ca01d6219c75a93768ae
|
File details
Details for the file fastncut-2.0.6-py3-none-any.whl.
File metadata
- Download URL: fastncut-2.0.6-py3-none-any.whl
- Upload date:
- Size: 7.6 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.13
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
e8adeb1be28d52ee9bd88a6b3439c94d0081cdd1968d8c79a8b4958452d7ace5
|
|
| MD5 |
013e57c036df301e4384e964f0d32e83
|
|
| BLAKE2b-256 |
6c30e0897a1212ce4176c6adad0e2f568f7c5a7b92d0e86e0196507e3c3ab523
|
