v0.3.2

Release notes

• Avoid an error with groupmod

Acknowledgements

• Satoshi Yamaji for reporting the issue

v0.3.1

Release notes

• Add error log for model reset during process is running

v0.3.0

Release notes

• Add tests
  • pytest
• Fix training epoch to log
  • batch_index starts from 1 in log
  • log at the end of log_interval instead of the beginning of it
• Add/update log messages
  • log at before/after each request
  • update "waiting" log
  • minor fix in a comment
• Implement download_model endpoint
• Implement uploading models (via reset)
  • when a request is multipart/form-data, an attached file is used to load state_dict(s) for resetting a model
  • if the uploaded model parameters are not compatible with a model, an error will be thrown
• Replace Conda with Mamba
  • replace Conda with Mamba
  • use the same environment.yml in all options (Docker, Singularity and Colab)
• Keep export results on the server
  • Fix zip name (.zip.zip to .zip)
• Avoid error on the CPU environment
  • make the gpus/ endpoint compatible with the CPU environment
• Explicitly kill all services before restart (Colab notebook)
  • the services can remain working when the notebook does not respond

Acknowledgements

• @tischi and Arif Ul Maula Khan for reporting issues (Fix training epoch to log, Avoid error on the CPU environment, Explicitly kill all services before restart (Colab notebook)) and suggestions (Add/update log messages, Implement download_model endpoint, Implement uploading models (via reset))
• Kojiro Mukai for reporting the issue on downloading the results after export

v0.2.0-keep-export

Fix zip name

- .zip.zip tp .zip

v0.2.0

Release notes

• Add XYZ flip operations in data augmentation
• Change MIN_AREA_ELLIPSOID from 20 to 9
• Automatically initialize a new model with the pretrained parameters
• Make detection algorithm compatible with 2D
• Make flow algorithm compatible with 2D
• Make export function compatible with 2D
• Update loss functions for detection (See details in the paper)
• Add tests for GitHub Actions
• Add get_gpus() for getting GPU info from the client software
• Implement upload endpoint for the client software
• Implement dataset endpoint for the client software
• Add environment.yml to reproduce the conda environment
• Implement logger that can be shared with the client software
• Update Colab notebook
• Use averaged training losses in log
• log_interval can be set as a parameter
• Reorganize Redis state management
• Reorganize cancel behavior
• Stop using probability to refine spot radii
• Move keep_axials from model to dataset
• Upgrade tensorflow to 2.4.0
• Organize model reset strategy
  • Versatile -> latest versatile model
  • Default -> self-supervised (detection) or random (flow)
  • URL -> load from the specified URL
• Update README

v0.1.1

Change list

• BugFix: avoid returning empty arrays in ellipsoid

v0.1.0-singularity

This release includes a Singularity definition file based on the ELEPHANT server v0.1.0.

Data

This release is for distributing data (e.g. pretrained model parameters).

ELEPHANT detection model pretrained parameters

• versatile2d.pth: trained with 2D datasets (BF-C2DL-HSC, BF-C2DL-MuSC, DIC-C2DH-HeLa, Fluo-C2DL-MSC, Fluo-N2DH-GOWT1, Fluo-N2DL-HeLa, PhC-C2DH-U373, PhC-C2DL-PSC) from the Cell Tracking Challenge
• versatile3d.pth: trained with 3D datasets (Fluo-C3DH-A549, Fluo-C3DH-H157, Fluo-C3DL-MDA231, Fluo-N3DH-CE, Fluo-N3DH-CHO) from the Cell Tracking Challenge and the PH dataset
• versatile3d_001.pth: same file as versatile3d.pth
• versatile3d_002.pth: trained with 3D datasets (Fluo-C3DH-A549, Fluo-C3DH-H157, Fluo-C3DL-MDA231, Fluo-N3DH-CHO) from the Cell Tracking Challenge and the PH dataset
• versatile3d_003.pth: trained with 3D datasets (Fluo-C3DH-A549, Fluo-C3DH-H157, Fluo-C3DL-MDA231, Fluo-N3DH-CE, Fluo-N3DH-CHO) from the Cell Tracking Challenge
• versatile3d_004.pth: trained with 3D datasets (Fluo-C3DH-A549, Fluo-C3DH-H157, Fluo-N3DH-CE, Fluo-N3DH-CHO) from the Cell Tracking Challenge

ELEPHANT flow model pretrained parameters

• Fluo-N3DH-CE_flow.pth: trained with the CE1 and CE2 datasets
• li13_flow_20201004.pth: trained with the PH dataset

v0.1.0

Fix a version number

version number was wrong