birdnet.geo.models package¶
Subpackages¶
- birdnet.geo.inference package
- Submodules
- birdnet.geo.inference.configs module
- birdnet.geo.inference.prediction_result module
GeoPredictionResultGeoPredictionResult.latitudeGeoPredictionResult.longitudeGeoPredictionResult.memory_size_MiBGeoPredictionResult.n_speciesGeoPredictionResult.species_idsGeoPredictionResult.species_listGeoPredictionResult.species_maskedGeoPredictionResult.species_probsGeoPredictionResult.to_arrow_table()GeoPredictionResult.to_csv()GeoPredictionResult.to_dataframe()GeoPredictionResult.to_set()GeoPredictionResult.to_structured_array()GeoPredictionResult.to_txt()GeoPredictionResult.week
- birdnet.geo.inference.session module
- Module contents
- birdnet.geo.models.v2_4 package
- Submodules
- birdnet.geo.models.v2_4.model module
GeoDownloaderBaseV2_4GeoModelV2_4GeoModelV2_4.backend_kwargsGeoModelV2_4.backend_typeGeoModelV2_4.get_model_type()GeoModelV2_4.get_n_classes()GeoModelV2_4.get_version()GeoModelV2_4.is_custom_modelGeoModelV2_4.load()GeoModelV2_4.load_custom()GeoModelV2_4.model_pathGeoModelV2_4.n_speciesGeoModelV2_4.predict()GeoModelV2_4.predict_session()GeoModelV2_4.species_list
- birdnet.geo.models.v2_4.pb module
GeoPBBackendFP32V2_4GeoPBBackendFP32V2_4.encoding_key()GeoPBBackendFP32V2_4.encoding_signature_name()GeoPBBackendFP32V2_4.input_key()GeoPBBackendFP32V2_4.precision()GeoPBBackendFP32V2_4.prediction_key()GeoPBBackendFP32V2_4.prediction_signature_name()GeoPBBackendFP32V2_4.supports_encoding()GeoPBBackendFP32V2_4.year_round_week_inputs()
GeoPBDownloaderV2_4
- birdnet.geo.models.v2_4.tf module
- Module contents
- birdnet.geo.models.v3_0 package
- Submodules
- birdnet.geo.models.v3_0.model module
GeoDownloaderBaseV3_0GeoModelV3_0GeoModelV3_0.backend_kwargsGeoModelV3_0.backend_typeGeoModelV3_0.get_model_type()GeoModelV3_0.get_n_classes()GeoModelV3_0.get_version()GeoModelV3_0.is_custom_modelGeoModelV3_0.load()GeoModelV3_0.load_custom()GeoModelV3_0.model_pathGeoModelV3_0.n_speciesGeoModelV3_0.predict()GeoModelV3_0.predict_session()GeoModelV3_0.species_list
- birdnet.geo.models.v3_0.tf module
- birdnet.geo.models.v3_0.pb module
GeoPBBackendFP32V3_0GeoPBBackendFP32V3_0.encoding_key()GeoPBBackendFP32V3_0.encoding_signature_name()GeoPBBackendFP32V3_0.input_key()GeoPBBackendFP32V3_0.precision()GeoPBBackendFP32V3_0.prediction_key()GeoPBBackendFP32V3_0.prediction_signature_name()GeoPBBackendFP32V3_0.supports_encoding()GeoPBBackendFP32V3_0.year_round_week_inputs()
GeoPBDownloaderV3_0
- birdnet.geo.models.v3_0.pt module
- birdnet.geo.models.v3_0.onnx module
- Module contents
Submodules¶
birdnet.geo.models.base module¶
- class birdnet.geo.models.base.GeoModelBase(model_path, species_list, is_custom_model, backend_type, backend_kwargs)¶
Bases:
ModelBase- property backend_kwargs: dict[str, Any]¶
- property backend_type: type[VersionedGeoBackendProtocol]¶
- abstractmethod classmethod get_version()¶
- Return type:
Literal['2.4','3.0']
- classmethod load(model_path, species_list, backend_type, backend_kwargs)¶
- Return type:
Self
- classmethod load_custom(model_path, species_list, backend_type, backend_kwargs, check_validity)¶
- Return type:
Self
- predict(latitude, longitude, /, *, week=None, year_round_aggregation='max', min_confidence=0.03, half_precision=False, device='CPU')¶
Predict the species present at a location, loading the backend for the call.
Opens a
predict_session(..)with the same options, runs it once and unloads the backend again, so the backend load, not the inference, dominates the call. For several locations or weeks, open one session and callrun(..)on it.- Return type:
- predict_session(*, min_confidence=0.03, half_precision=False, device='CPU')¶
Open a session that keeps the backend loaded between
run(..)calls.Entering the session loads the backend once; each
run(latitude, longitude, week=..)then costs one inference. Use it for several locations or weeks.- Return type: