batchgeneratorsv2

This repository is work in progress. If builds upon the batchgenerators framework but makes several key changes to the transforms:

  1. Transforms now explicitly distinguish between data types: images, segmentation, pixel-wise regression target, keypoints, bbox
  2. All transforms have been reimplemented from scratch with a focus on performance. In case of performance parity between previous numpy and new torch-based implementations, preference is given to pytorch.
  3. Transforms are applied on a sample level, not a batch level as was done previously!

Caveats:

  • performance is optimized for CPU. GPU-based data augmentation is not supported (implementation may use numpy etc) and will not be supported
  • currently this repository only covers a small subset of the transforms available in batchgenerators. Feel free to contribute more

How to contribute

We are happy to accept PRs that further optimize performance and extend the available transformations!

  • Please provide benchmarking results relative to the old batchgenerators implementation (if applicable)
  • Please stick to the current transform template!

Acknowledgements

batchgeneratorsv2 developed and maintained by the Applied Computer Vision Lab (ACVL) of Helmholtz Imaging and the Division of Medical Image Computing at the German Cancer Research Center (DKFZ).

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
Latest release

1 maintainer

PyPI data
Data sourced directly from PyPI's database.
Avatar for isenseef from gravatar.com isenseef

Credits

Author: Helmholtz Imaging Applied Computer Vision Lab

License

Apache Software License (Apache License)

Requires

Python >=3.9

Tags

deep learning image segmentation semantic segmentation medical image analysis medical image segmentation nnU-Net nnunet

Classifiers

Report project as malware

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

batchgeneratorsv2-0.3.5.tar.gz (53.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

batchgeneratorsv2-0.3.5-py3-none-any.whl (76.8 kB view details)

Uploaded Python 3

File details

Details for the file batchgeneratorsv2-0.3.5.tar.gz.

File metadata

  • Download URL: batchgeneratorsv2-0.3.5.tar.gz
  • Upload date:
  • Size: 53.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for batchgeneratorsv2-0.3.5.tar.gz
Algorithm Hash digest
SHA256 7d75a421e7f18076308209f55af60582227ce061e03714a9e5a0c9dcddea3593
MD5 665668862aafb2604fb2e5cfc724c8f3
BLAKE2b-256 742f235291df11c8476c95b77c4447ba4f066ae1e54c9266e18bf8023d4783fe

See more details on using hashes here.

Provenance

The following attestation bundles were made for batchgeneratorsv2-0.3.5.tar.gz:

Publisher: publish.yml on MIC-DKFZ/batchgeneratorsv2

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file batchgeneratorsv2-0.3.5-py3-none-any.whl.

File metadata

File hashes

Hashes for batchgeneratorsv2-0.3.5-py3-none-any.whl
Algorithm Hash digest
SHA256 a1773332bf41530a47c4c3856f43cee658f06e825bf964106e9c5422c5b4669a
MD5 6c25fabd8e1fd2fa7febec890252d01d
BLAKE2b-256 3def3233c320ffbf12a916511606398b7405d63c0e01646d1f39484f1d605c40

See more details on using hashes here.

Provenance

The following attestation bundles were made for batchgeneratorsv2-0.3.5-py3-none-any.whl:

Publisher: publish.yml on MIC-DKFZ/batchgeneratorsv2

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page