Changelog#
All project's changes will be documented here.
[3.2]#
Added#
- Load a FittedParquetDataset, ExplanationArtifact, Filter or TrainedModelArtifact instances by
idornameusingget_by_idandget_by_nameclass methods. - Load all FittedParquetDataset, ExplanationArtifact, Filter or TrainedModelArtifact instances of a project using
load_allclass method. - Delete a FittedParquetDataset, ExplanationArtifact, Filter or TrainedModelArtifact instances using
deletemethod. - Updating TrainedModelArtifact or ExplanationArtifact instances disabled, except for
nameanddescriptionattributes. - Updating Filter instances attributes
dataset,min_indexandmax_indexdisabled. - Updating FittedParquetDataset instances attributes disabled.
- Saving FittedParquetDataset and Filter using
savemethod. - Documentation on Xpdeep Platform Accesss
Changed#
- Additional feature types available.
ImageFeatureAugmentationis renamedFeatureAugmentation.ExplainableFeaturefeature_augmentationattribute is renamedaugmentation.Project.list_fitted_datasetsmethod replaced byFilter.load_all.Project.list_trained_modelsmethod replaced byTrainedModelArtifact.load_allProject.list_explanationsmethod replaced by ExplanationArtifact.load_all`Project.list_computed_statisticsmethod replaced byFittedParquetDataset.load_computed_statisticsFittedParquetDataset.artifact_idproperty replaced byFittedParquetDataset.id- Building an
XpdeepModelusingfrom_torchclass method requires an example dataset instead of aFittedSchema - The trainer loss must be an
XpdeepLoss - Remove
target_homogeneity_pruning_thresholdofModelDecisionGraphParametersparameters - Rework tutorials to use more default values
Removed#
split_nameis deleted inParquetDatasetArtifactInsert.target_homogeneity_pruning_thresholdandreset_optimizer_on_pruningare deprecated and will be removed in the next release.
[3.1]#
Added#
ImageFeaturetype.- Data augmentation is available for
ImageFeaturewithImageFeatureAugmentation, backed bytorchvision. - Object Detection task, with a tutorial, and provided models.
- Handle error on creating or getting a project with same name as another one you do not have access to.
Fixed#
- Serialization of
TorchPreprocessortransform and inverse_transform methods was incorrect. ApiErrorwhen theAnalyzedSchemareturned aBaseFeatureif no match was found.- Bugs related to duplicated insertions of Filters and Datasets.
- Bug related to updating project name and description.
Changed#
TorchModelis replaced byApiModulefor model serialization.is_post_hocis replaced byfrozen_modelinModelDecisionGraphParameters.PostHocTraineris replaced byFrozenModelTrainer.IndexMetadatashould be added in your parquet file and specified in theSchema.