Skip to main content

README

TabNet : Attentive Interpretable Tabular Learning

  • this is maintained fork version of dreamquark-ai/tabnet with some changes and improvements.

  • it uses pytorch metrics instead of numpy metrics, and also enhanced predictions & evaluation for GPU CUDA enhancement.

  • expect more changes in the future.

  • for the record and license policy assume everything is changed.

  • thanks & credits to dreamquark-ai team for the implementation and research.

This is a pyTorch implementation of Tabnet (Arik, S. O., & Pfister, T. (2019). TabNet: Attentive Interpretable Tabular Learning. arXiv preprint arXiv:1908.07442.) https://arxiv.org/pdf/1908.07442.pdf. Please note that some different choices have been made overtime to improve the library which can differ from the orginal paper.

Release files for eh-pytorch-tabnet 4.4.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for eh-pytorch-tabnet 4.4.0
File Size Uploaded
eh_pytorch_tabnet-4.4.0.tar.gz 36.1 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for eh-pytorch-tabnet 4.4.0
File Interpreter ABI Platform
eh_pytorch_tabnet-4.4.0-py3-none-any.whl Python 3 none any Details

Total release size: 78.2 kB

Release files / eh_pytorch_tabnet-4.4.0.tar.gz

Download URL eh_pytorch_tabnet-4.4.0.tar.gz
Size 36.1 kB
Tags Source
SHA-256 checksum
How to use checksums
46d85a876ff389d3e7ba270ed3eb0134c376a707a3500a5617dc1d305ce6b864
BLAKE2b-256 checksum
How to use checksums
09900c267682ad893789e87ed21187bdb9e258cdeb42c866b44404ff06a35ef5
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.5.24

Release files / eh_pytorch_tabnet-4.4.0-py3-none-any.whl

Download URL eh_pytorch_tabnet-4.4.0-py3-none-any.whl
Size 42.1 kB
Tags Python 3
SHA-256 checksum
How to use checksums
4c778d3c5a8eebb0ef4060a16b4c651ed130b8386e43db53c2e29ffc15679004
BLAKE2b-256 checksum
How to use checksums
457827902ca56cbc0b5508a8d85d7427effbc532a78ac5568c849602c43d88dd
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.5.24

Release history Release notifications | RSS feed

This release

4.4.0 This release

2 release files

4.3.0

2 release files

4.2.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page