bacpipe.tests.test_embedding_creation

Functions

clustering_pipeline(model_name, ...[, ...])	Clustering pipeline, generating clusterings based on the settings file.
ground_truth_by_model(model, audio_dir[, ...])	Generate ground truth labels that are mapped onto the timestamps of a model, based on the model-specific input lengths.
make_set_paths_func(audio_dir[, ...])
probing_pipeline(model_name, ground_truth, ...)	Probing pipeline consisting of building the classifier, evaluating it and saving metrics and plots of performance.
run_pipeline_for_single_model(model_name, ...)	Run the bacpipe pipeline, including embedding generation, classification using the pretrained classifier (if included), dimensionality reduction (if passed), and plotting of visualization to files.
test_benchmarking(model, device, ...)
test_embedding_dimensions(model, kwargs)
test_embedding_generation(model, device, ...)
test_evaluation(model, overwrite, device, ...)

bacpipe.tests.test_embedding_creation.test_benchmarking(model, device, only_embed_annotations, kwargs)

bacpipe.tests.test_embedding_creation.test_embedding_dimensions(model, kwargs)

bacpipe.tests.test_embedding_creation.test_embedding_generation(model, device, check_if_already_processed, check_if_already_dim_reduced, only_embed_annotations, kwargs)

bacpipe.tests.test_embedding_creation.test_evaluation(model, overwrite, device, only_embed_annotations, kwargs)