2.6.0

What's Changed

• Refactor load_model to use factories for settings and model by @florian-huber in #281
• Added notebook for creating supplementary information section 11 by @niekdejonge in #282
• Pytorch update by @florian-huber in #280

Full Changelog: 2.5.5...2.6.0

2.5.5

What's Changed

• remove unused torchvision and update sonarqube pipeline by @florian-huber in #279

Full Changelog: 2.5.4...2.5.5

2.5.4

What's Changed

• Update revisions by @niekdejonge in #275
• add progress bar to embedding computations by @florian-huber in #276

Full Changelog: 2.5.3...2.5.4

2.5.3

What's Changed

• Remove monte carlo since not supported for current models by @niekdejonge in #271
• Update minimum matchms version in setup.py by @niekdejonge in #274
• Update revisions by @niekdejonge in #273

Full Changelog: 2.5.2...2.5.3

2.5.2

What's Changed

• Update tutorials by @niekdejonge in #266
• move to numpy >=2 by @florian-huber in #268

Full Changelog: 2.5.1...2.5.2

2.5.1

What's Changed

• Alternative remove_diagonal implementation by @florian-huber in #264
• restrict torch until new model load/save is implemented by @florian-huber in #265

Full Changelog: 2.5.0...2.5.1

2.5.0

What's Changed

• Remove outdated notebooks and update notebooks for ms2deepscore 2 by @niekdejonge in #238
• Add notebook for optimizing sampling algorithm by @niekdejonge in #256
• Added saving history as json file (instead of only plotting) by @niekdejonge in #257
• Add notebook hyperparemeter optimization by @niekdejonge in #258
• Add notebooks benchmarking by @niekdejonge in #259
• Add notebooks benchmarking by @niekdejonge in #261
• Added notebook for comparison with modified cosine scores by @niekdejonge in #262
• Add notebooks analyzing the case studies by @niekdejonge in #255

Full Changelog: 2.4.0...2.5.0

2.4.0

What's Changed

• Update sampling algorithm by @niekdejonge in #253

Full Changelog: 2.3.0...2.4.0

2.3.0

ms2deepscore 2.3.0

Added

• New plotting functions for benchmarking #244

Changed

• Integrated new plotting functions in automated training pipeline #244
• Removed automatic storing of benchmarking scores #244
• Integrated loss calculation for validation loss and plots #244
• Validation loss uses all spectrum pairs instead of only 1 spectrum per inchikey #244
• Code refactoring and code linting.

Fixed

• Fingerprint type and number of bits specified in the settings is now correctly used in training and validation (before was set to default values in some instances) #244 and #251

Removed

• Removed version warning #249

Full Changelog: 2.2.0...2.3.0

2.2.0

What's Changed

• Adding case study notebooks by @niekdejonge in #229
• Switch linter (and linting style) from pylint + prospector to ruff #240
• Clearer documentation and naming to run training from existing splits #239
• empty cache to avoid memory leak by @florian-huber #243