HomeDocsForumStudio

classify_api module

ClassifyApi

class edgeimpulse_api.api.classify_api.ClassifyApi(
		api_client=None
)

Parameters

  • api_client=None

Methods

classify_image

edgeimpulse_api.api.classify_api.classify_image(
		self,
		project_id: Annotated[pydantic.types.StrictInt, FieldInfo(default=Ellipsis, description='Project ID', extra={})],
		image: pydantic.types.StrictStr,
		impulse_id: Annotated[pydantic.types.StrictInt | None, FieldInfo(default=PydanticUndefined, description='Impulse ID. If this is unset then the default impulse is used.', extra={})] = None,
		**kwargs
) ‑> edgeimpulse_api.models.test_pretrained_model_response.TestPretrainedModelResponse

Classify an image

Test out a trained impulse (using a posted image).

Parameters

  • self

  • project_id: Annotated[pydantic.types.StrictInt, FieldInfo(default=Ellipsis, description='Project ID', extra={})]

  • image: pydantic.types.StrictStr

  • impulse_id: Annotated[pydantic.types.StrictInt | None, FieldInfo(default=PydanticUndefined, description='Impulse ID. If this is unset then the default impulse is used.', extra={})] = None

  • **kwargs

Return

edgeimpulse_api.models.test_pretrained_model_response.TestPretrainedModelResponse

classify_sample

edgeimpulse_api.api.classify_api.classify_sample(
		self,
		project_id: Annotated[pydantic.types.StrictInt, FieldInfo(default=Ellipsis, description='Project ID', extra={})],
		sample_id: Annotated[pydantic.types.StrictInt, FieldInfo(default=Ellipsis, description='Sample ID', extra={})],
		include_debug_info: Annotated[pydantic.types.StrictBool | None, FieldInfo(default=PydanticUndefined, description='Whether to return the debug information from FOMO classification.', extra={})] = None,
		impulse_id: Annotated[pydantic.types.StrictInt | None, FieldInfo(default=PydanticUndefined, description='Impulse ID. If this is unset then the default impulse is used.', extra={})] = None,
		**kwargs
) ‑> edgeimpulse_api.models.classify_sample_response.ClassifySampleResponse

Classify sample (deprecated)

This API is deprecated, use classifySampleV2 instead (/v1/api/{projectId}/classify/v2/{sampleId}). Classify a complete file against the current impulse. This will move the sliding window (dependent on the sliding window length and the sliding window increase parameters in the impulse) over the complete file, and classify for every window that is extracted.

Parameters

  • self

  • project_id: Annotated[pydantic.types.StrictInt, FieldInfo(default=Ellipsis, description='Project ID', extra={})]

  • sample_id: Annotated[pydantic.types.StrictInt, FieldInfo(default=Ellipsis, description='Sample ID', extra={})]

  • include_debug_info: Annotated[pydantic.types.StrictBool | None, FieldInfo(default=PydanticUndefined, description='Whether to return the debug information from FOMO classification.', extra={})] = None

  • impulse_id: Annotated[pydantic.types.StrictInt | None, FieldInfo(default=PydanticUndefined, description='Impulse ID. If this is unset then the default impulse is used.', extra={})] = None

  • **kwargs

Return

edgeimpulse_api.models.classify_sample_response.ClassifySampleResponse

classify_sample_by_learn_block

edgeimpulse_api.api.classify_api.classify_sample_by_learn_block(
		self,
		project_id: Annotated[pydantic.types.StrictInt, FieldInfo(default=Ellipsis, description='Project ID', extra={})],
		sample_id: Annotated[pydantic.types.StrictInt, FieldInfo(default=Ellipsis, description='Sample ID', extra={})],
		block_id: Annotated[pydantic.types.StrictInt, FieldInfo(default=Ellipsis, description='Block ID', extra={})],
		**kwargs
) ‑> edgeimpulse_api.models.classify_sample_response.ClassifySampleResponse

Classify sample by learn block

This API is deprecated, use classifySampleByLearnBlockV2 (/v1/api/{projectId}/classify/anomaly-gmm/v2/{blockId}/{sampleId}) instead. Classify a complete file against the specified learn block. This will move the sliding window (dependent on the sliding window length and the sliding window increase parameters in the impulse) over the complete file, and classify for every window that is extracted.

Parameters

  • self

  • project_id: Annotated[pydantic.types.StrictInt, FieldInfo(default=Ellipsis, description='Project ID', extra={})]

  • sample_id: Annotated[pydantic.types.StrictInt, FieldInfo(default=Ellipsis, description='Sample ID', extra={})]

  • block_id: Annotated[pydantic.types.StrictInt, FieldInfo(default=Ellipsis, description='Block ID', extra={})]

  • **kwargs

Return

edgeimpulse_api.models.classify_sample_response.ClassifySampleResponse

classify_sample_by_learn_block_v2

edgeimpulse_api.api.classify_api.classify_sample_by_learn_block_v2(
		self,
		project_id: Annotated[pydantic.types.StrictInt, FieldInfo(default=Ellipsis, description='Project ID', extra={})],
		sample_id: Annotated[pydantic.types.StrictInt, FieldInfo(default=Ellipsis, description='Sample ID', extra={})],
		block_id: Annotated[pydantic.types.StrictInt, FieldInfo(default=Ellipsis, description='Block ID', extra={})],
		variant: Annotated[edgeimpulse_api.models.keras_model_variant_enum.KerasModelVariantEnum | None, FieldInfo(default=PydanticUndefined, description='Keras model variant', extra={})] = None,
		truncate_structured_labels: Annotated[pydantic.types.StrictBool | None, FieldInfo(default=PydanticUndefined, description='If true, only a slice of labels will be returned for samples with multiple labels.', extra={})] = None,
		**kwargs
) ‑> edgeimpulse_api.models.classify_sample_v2200_response.ClassifySampleV2200Response

Classify sample by learn block

Classify a complete file against the specified learn block. This will move the sliding window (dependent on the sliding window length and the sliding window increase parameters in the impulse) over the complete file, and classify for every window that is extracted. Depending on the size of your file, whether your sample is resampled, and whether the result is cached you'll get either the result or a job back. If you receive a job, then wait for the completion of the job, and then call this function again to receive the results. The unoptimized (float32) model is used by default, and classification with an optimized (int8) model can be slower.

Parameters

  • self

  • project_id: Annotated[pydantic.types.StrictInt, FieldInfo(default=Ellipsis, description='Project ID', extra={})]

  • sample_id: Annotated[pydantic.types.StrictInt, FieldInfo(default=Ellipsis, description='Sample ID', extra={})]

  • block_id: Annotated[pydantic.types.StrictInt, FieldInfo(default=Ellipsis, description='Block ID', extra={})]

  • variant: Annotated[edgeimpulse_api.models.keras_model_variant_enum.KerasModelVariantEnum | None, FieldInfo(default=PydanticUndefined, description='Keras model variant', extra={})] = None

  • truncate_structured_labels: Annotated[pydantic.types.StrictBool | None, FieldInfo(default=PydanticUndefined, description='If true, only a slice of labels will be returned for samples with multiple labels.', extra={})] = None

  • **kwargs

Return

edgeimpulse_api.models.classify_sample_v2200_response.ClassifySampleV2200Response

classify_sample_for_variants

edgeimpulse_api.api.classify_api.classify_sample_for_variants(
		self,
		project_id: Annotated[pydantic.types.StrictInt, FieldInfo(default=Ellipsis, description='Project ID', extra={})],
		sample_id: Annotated[pydantic.types.StrictInt, FieldInfo(default=Ellipsis, description='Sample ID', extra={})],
		variants: Annotated[pydantic.types.StrictStr, FieldInfo(default=Ellipsis, description='List of keras model variants, given as a JSON string', extra={})],
		include_debug_info: Annotated[pydantic.types.StrictBool | None, FieldInfo(default=PydanticUndefined, description='Whether to return the debug information from FOMO classification.', extra={})] = None,
		impulse_id: Annotated[pydantic.types.StrictInt | None, FieldInfo(default=PydanticUndefined, description='Impulse ID. If this is unset then the default impulse is used.', extra={})] = None,
		truncate_structured_labels: Annotated[pydantic.types.StrictBool | None, FieldInfo(default=PydanticUndefined, description='If true, only a slice of labels will be returned for samples with multiple labels.', extra={})] = None,
		**kwargs
) ‑> edgeimpulse_api.models.classify_sample_for_variants200_response.ClassifySampleForVariants200Response

Classify sample for the given set of variants

Classify a complete file against the current impulse, for all given variants. Depending on the size of your file and whether the sample is resampled, you may get a job ID in the response.

Parameters

  • self

  • project_id: Annotated[pydantic.types.StrictInt, FieldInfo(default=Ellipsis, description='Project ID', extra={})]

  • sample_id: Annotated[pydantic.types.StrictInt, FieldInfo(default=Ellipsis, description='Sample ID', extra={})]

  • variants: Annotated[pydantic.types.StrictStr, FieldInfo(default=Ellipsis, description='List of keras model variants, given as a JSON string', extra={})]

  • include_debug_info: Annotated[pydantic.types.StrictBool | None, FieldInfo(default=PydanticUndefined, description='Whether to return the debug information from FOMO classification.', extra={})] = None

  • impulse_id: Annotated[pydantic.types.StrictInt | None, FieldInfo(default=PydanticUndefined, description='Impulse ID. If this is unset then the default impulse is used.', extra={})] = None

  • truncate_structured_labels: Annotated[pydantic.types.StrictBool | None, FieldInfo(default=PydanticUndefined, description='If true, only a slice of labels will be returned for samples with multiple labels.', extra={})] = None

  • **kwargs

Return

edgeimpulse_api.models.classify_sample_for_variants200_response.ClassifySampleForVariants200Response

classify_sample_v2

edgeimpulse_api.api.classify_api.classify_sample_v2(
		self,
		project_id: Annotated[pydantic.types.StrictInt, FieldInfo(default=Ellipsis, description='Project ID', extra={})],
		sample_id: Annotated[pydantic.types.StrictInt, FieldInfo(default=Ellipsis, description='Sample ID', extra={})],
		include_debug_info: Annotated[pydantic.types.StrictBool | None, FieldInfo(default=PydanticUndefined, description='Whether to return the debug information from FOMO classification.', extra={})] = None,
		variant: Annotated[edgeimpulse_api.models.keras_model_variant_enum.KerasModelVariantEnum | None, FieldInfo(default=PydanticUndefined, description='Keras model variant', extra={})] = None,
		impulse_id: Annotated[pydantic.types.StrictInt | None, FieldInfo(default=PydanticUndefined, description='Impulse ID. If this is unset then the default impulse is used.', extra={})] = None,
		truncate_structured_labels: Annotated[pydantic.types.StrictBool | None, FieldInfo(default=PydanticUndefined, description='If true, only a slice of labels will be returned for samples with multiple labels.', extra={})] = None,
		**kwargs
) ‑> edgeimpulse_api.models.classify_sample_v2200_response.ClassifySampleV2200Response

Classify sample

Classify a complete file against the current impulse. This will move the sliding window (dependent on the sliding window length and the sliding window increase parameters in the impulse) over the complete file, and classify for every window that is extracted. Depending on the size of your file, whether your sample is resampled, and whether the result is cached you'll get either the result or a job back. If you receive a job, then wait for the completion of the job, and then call this function again to receive the results. The unoptimized (float32) model is used by default, and classification with an optimized (int8) model can be slower.

Parameters

  • self

  • project_id: Annotated[pydantic.types.StrictInt, FieldInfo(default=Ellipsis, description='Project ID', extra={})]

  • sample_id: Annotated[pydantic.types.StrictInt, FieldInfo(default=Ellipsis, description='Sample ID', extra={})]

  • include_debug_info: Annotated[pydantic.types.StrictBool | None, FieldInfo(default=PydanticUndefined, description='Whether to return the debug information from FOMO classification.', extra={})] = None

  • variant: Annotated[edgeimpulse_api.models.keras_model_variant_enum.KerasModelVariantEnum | None, FieldInfo(default=PydanticUndefined, description='Keras model variant', extra={})] = None

  • impulse_id: Annotated[pydantic.types.StrictInt | None, FieldInfo(default=PydanticUndefined, description='Impulse ID. If this is unset then the default impulse is used.', extra={})] = None

  • truncate_structured_labels: Annotated[pydantic.types.StrictBool | None, FieldInfo(default=PydanticUndefined, description='If true, only a slice of labels will be returned for samples with multiple labels.', extra={})] = None

  • **kwargs

Return

edgeimpulse_api.models.classify_sample_v2200_response.ClassifySampleV2200Response

get_classify_job_result

edgeimpulse_api.api.classify_api.get_classify_job_result(
		self,
		project_id: Annotated[pydantic.types.StrictInt, FieldInfo(default=Ellipsis, description='Project ID', extra={})],
		feature_explorer_only: Annotated[pydantic.types.StrictBool | None, FieldInfo(default=PydanticUndefined, description='Whether to get only the classification results relevant to the feature explorer.', extra={})] = None,
		variant: Annotated[edgeimpulse_api.models.keras_model_variant_enum.KerasModelVariantEnum | None, FieldInfo(default=PydanticUndefined, description='Keras model variant', extra={})] = None,
		impulse_id: Annotated[pydantic.types.StrictInt | None, FieldInfo(default=PydanticUndefined, description='Impulse ID. If this is unset then the default impulse is used.', extra={})] = None,
		truncate_structured_labels: Annotated[pydantic.types.StrictBool | None, FieldInfo(default=PydanticUndefined, description='If true, only a slice of labels will be returned for samples with multiple labels.', extra={})] = None,
		labels: Annotated[pydantic.types.StrictStr | None, FieldInfo(default=PydanticUndefined, description='Only include samples with a label within the given list of labels, given as a JSON string', extra={})] = None,
		filename: Annotated[pydantic.types.StrictStr | None, FieldInfo(default=PydanticUndefined, description='Only include samples whose filename includes the given filename', extra={})] = None,
		max_length: Annotated[pydantic.types.StrictInt | None, FieldInfo(default=PydanticUndefined, description='Only include samples shorter than the given length, in milliseconds', extra={})] = None,
		min_length: Annotated[pydantic.types.StrictInt | None, FieldInfo(default=PydanticUndefined, description='Only include samples longer than the given length, in milliseconds', extra={})] = None,
		min_frequency: Annotated[float | None, FieldInfo(default=PydanticUndefined, description='Only include samples with higher frequency than given frequency, in hertz', extra={})] = None,
		max_frequency: Annotated[float | None, FieldInfo(default=PydanticUndefined, description='Only include samples with lower frequency than given frequency, in hertz', extra={})] = None,
		signature_validity: Annotated[pydantic.types.StrictStr | None, FieldInfo(default=PydanticUndefined, description='Include samples with either valid or invalid signatures', extra={})] = None,
		min_label: Annotated[float | None, FieldInfo(default=PydanticUndefined, description='Only include samples with a label >= this value', extra={})] = None,
		max_label: Annotated[float | None, FieldInfo(default=PydanticUndefined, description='Only include samples with a label < this value', extra={})] = None,
		search: Annotated[pydantic.types.StrictStr | None, FieldInfo(default=PydanticUndefined, description='Search query', extra={})] = None,
		data_type: Annotated[pydantic.types.StrictStr | None, FieldInfo(default=PydanticUndefined, description='Include only samples with a particular data type', extra={})] = None,
		min_id: Annotated[float | None, FieldInfo(default=PydanticUndefined, description='Include only samples with an ID >= this value', extra={})] = None,
		max_id: Annotated[float | None, FieldInfo(default=PydanticUndefined, description='Include only samples with an ID < this value', extra={})] = None,
		metadata: Annotated[pydantic.types.StrictStr | None, FieldInfo(default=PydanticUndefined, description='Filter samples by metadata key-value pairs, provided as a JSON string. Each filter item in the list is combined using a logical OR. To include samples without any metadata, use: { "no_metadata": true }. ', extra={})] = None,
		min_date: Annotated[datetime.datetime | None, FieldInfo(default=PydanticUndefined, description='Only include samples that where added after the date given', extra={})] = None,
		max_date: Annotated[datetime.datetime | None, FieldInfo(default=PydanticUndefined, description='Only include samples that were added before the date given', extra={})] = None,
		**kwargs
) ‑> edgeimpulse_api.models.classify_job_response.ClassifyJobResponse

Classify job result

Get classify job result, containing the result for the complete testing dataset.

Parameters

  • self

  • project_id: Annotated[pydantic.types.StrictInt, FieldInfo(default=Ellipsis, description='Project ID', extra={})]

  • feature_explorer_only: Annotated[pydantic.types.StrictBool | None, FieldInfo(default=PydanticUndefined, description='Whether to get only the classification results relevant to the feature explorer.', extra={})] = None

  • variant: Annotated[edgeimpulse_api.models.keras_model_variant_enum.KerasModelVariantEnum | None, FieldInfo(default=PydanticUndefined, description='Keras model variant', extra={})] = None

  • impulse_id: Annotated[pydantic.types.StrictInt | None, FieldInfo(default=PydanticUndefined, description='Impulse ID. If this is unset then the default impulse is used.', extra={})] = None

  • truncate_structured_labels: Annotated[pydantic.types.StrictBool | None, FieldInfo(default=PydanticUndefined, description='If true, only a slice of labels will be returned for samples with multiple labels.', extra={})] = None

  • labels: Annotated[pydantic.types.StrictStr | None, FieldInfo(default=PydanticUndefined, description='Only include samples with a label within the given list of labels, given as a JSON string', extra={})] = None

  • filename: Annotated[pydantic.types.StrictStr | None, FieldInfo(default=PydanticUndefined, description='Only include samples whose filename includes the given filename', extra={})] = None

  • max_length: Annotated[pydantic.types.StrictInt | None, FieldInfo(default=PydanticUndefined, description='Only include samples shorter than the given length, in milliseconds', extra={})] = None

  • min_length: Annotated[pydantic.types.StrictInt | None, FieldInfo(default=PydanticUndefined, description='Only include samples longer than the given length, in milliseconds', extra={})] = None

  • min_frequency: Annotated[float | None, FieldInfo(default=PydanticUndefined, description='Only include samples with higher frequency than given frequency, in hertz', extra={})] = None

  • max_frequency: Annotated[float | None, FieldInfo(default=PydanticUndefined, description='Only include samples with lower frequency than given frequency, in hertz', extra={})] = None

  • signature_validity: Annotated[pydantic.types.StrictStr | None, FieldInfo(default=PydanticUndefined, description='Include samples with either valid or invalid signatures', extra={})] = None

  • min_label: Annotated[float | None, FieldInfo(default=PydanticUndefined, description='Only include samples with a label >= this value', extra={})] = None

  • max_label: Annotated[float | None, FieldInfo(default=PydanticUndefined, description='Only include samples with a label < this value', extra={})] = None

  • search: Annotated[pydantic.types.StrictStr | None, FieldInfo(default=PydanticUndefined, description='Search query', extra={})] = None

  • data_type: Annotated[pydantic.types.StrictStr | None, FieldInfo(default=PydanticUndefined, description='Include only samples with a particular data type', extra={})] = None

  • min_id: Annotated[float | None, FieldInfo(default=PydanticUndefined, description='Include only samples with an ID >= this value', extra={})] = None

  • max_id: Annotated[float | None, FieldInfo(default=PydanticUndefined, description='Include only samples with an ID < this value', extra={})] = None

  • metadata: Annotated[pydantic.types.StrictStr | None, FieldInfo(default=PydanticUndefined, description='Filter samples by metadata key-value pairs, provided as a JSON string. Each filter item in the list is combined using a logical OR. To include samples without any metadata, use: { "no_metadata": true }. ', extra={})] = None

  • min_date: Annotated[datetime.datetime | None, FieldInfo(default=PydanticUndefined, description='Only include samples that where added after the date given', extra={})] = None

  • max_date: Annotated[datetime.datetime | None, FieldInfo(default=PydanticUndefined, description='Only include samples that were added before the date given', extra={})] = None

  • **kwargs

Return

edgeimpulse_api.models.classify_job_response.ClassifyJobResponse

get_classify_job_result_page

edgeimpulse_api.api.classify_api.get_classify_job_result_page(
		self,
		project_id: Annotated[pydantic.types.StrictInt, FieldInfo(default=Ellipsis, description='Project ID', extra={})],
		limit: Annotated[pydantic.types.StrictInt | None, FieldInfo(default=PydanticUndefined, description='Maximum number of results', extra={})] = None,
		offset: Annotated[pydantic.types.StrictInt | None, FieldInfo(default=PydanticUndefined, description='Offset in results, can be used in conjunction with LimitResultsParameter to implement paging.', extra={})] = None,
		variant: Annotated[edgeimpulse_api.models.keras_model_variant_enum.KerasModelVariantEnum | None, FieldInfo(default=PydanticUndefined, description='Keras model variant', extra={})] = None,
		impulse_id: Annotated[pydantic.types.StrictInt | None, FieldInfo(default=PydanticUndefined, description='Impulse ID. If this is unset then the default impulse is used.', extra={})] = None,
		truncate_structured_labels: Annotated[pydantic.types.StrictBool | None, FieldInfo(default=PydanticUndefined, description='If true, only a slice of labels will be returned for samples with multiple labels.', extra={})] = None,
		labels: Annotated[pydantic.types.StrictStr | None, FieldInfo(default=PydanticUndefined, description='Only include samples with a label within the given list of labels, given as a JSON string', extra={})] = None,
		filename: Annotated[pydantic.types.StrictStr | None, FieldInfo(default=PydanticUndefined, description='Only include samples whose filename includes the given filename', extra={})] = None,
		max_length: Annotated[pydantic.types.StrictInt | None, FieldInfo(default=PydanticUndefined, description='Only include samples shorter than the given length, in milliseconds', extra={})] = None,
		min_length: Annotated[pydantic.types.StrictInt | None, FieldInfo(default=PydanticUndefined, description='Only include samples longer than the given length, in milliseconds', extra={})] = None,
		min_frequency: Annotated[float | None, FieldInfo(default=PydanticUndefined, description='Only include samples with higher frequency than given frequency, in hertz', extra={})] = None,
		max_frequency: Annotated[float | None, FieldInfo(default=PydanticUndefined, description='Only include samples with lower frequency than given frequency, in hertz', extra={})] = None,
		signature_validity: Annotated[pydantic.types.StrictStr | None, FieldInfo(default=PydanticUndefined, description='Include samples with either valid or invalid signatures', extra={})] = None,
		min_label: Annotated[float | None, FieldInfo(default=PydanticUndefined, description='Only include samples with a label >= this value', extra={})] = None,
		max_label: Annotated[float | None, FieldInfo(default=PydanticUndefined, description='Only include samples with a label < this value', extra={})] = None,
		search: Annotated[pydantic.types.StrictStr | None, FieldInfo(default=PydanticUndefined, description='Search query', extra={})] = None,
		data_type: Annotated[pydantic.types.StrictStr | None, FieldInfo(default=PydanticUndefined, description='Include only samples with a particular data type', extra={})] = None,
		min_id: Annotated[float | None, FieldInfo(default=PydanticUndefined, description='Include only samples with an ID >= this value', extra={})] = None,
		max_id: Annotated[float | None, FieldInfo(default=PydanticUndefined, description='Include only samples with an ID < this value', extra={})] = None,
		metadata: Annotated[pydantic.types.StrictStr | None, FieldInfo(default=PydanticUndefined, description='Filter samples by metadata key-value pairs, provided as a JSON string. Each filter item in the list is combined using a logical OR. To include samples without any metadata, use: { "no_metadata": true }. ', extra={})] = None,
		min_date: Annotated[datetime.datetime | None, FieldInfo(default=PydanticUndefined, description='Only include samples that where added after the date given', extra={})] = None,
		max_date: Annotated[datetime.datetime | None, FieldInfo(default=PydanticUndefined, description='Only include samples that were added before the date given', extra={})] = None,
		**kwargs
) ‑> edgeimpulse_api.models.classify_job_response_page.ClassifyJobResponsePage

Single page of a classify job result

Get classify job result, containing the predictions for a given page.

Parameters

  • self

  • project_id: Annotated[pydantic.types.StrictInt, FieldInfo(default=Ellipsis, description='Project ID', extra={})]

  • limit: Annotated[pydantic.types.StrictInt | None, FieldInfo(default=PydanticUndefined, description='Maximum number of results', extra={})] = None

  • offset: Annotated[pydantic.types.StrictInt | None, FieldInfo(default=PydanticUndefined, description='Offset in results, can be used in conjunction with LimitResultsParameter to implement paging.', extra={})] = None

  • variant: Annotated[edgeimpulse_api.models.keras_model_variant_enum.KerasModelVariantEnum | None, FieldInfo(default=PydanticUndefined, description='Keras model variant', extra={})] = None

  • impulse_id: Annotated[pydantic.types.StrictInt | None, FieldInfo(default=PydanticUndefined, description='Impulse ID. If this is unset then the default impulse is used.', extra={})] = None

  • truncate_structured_labels: Annotated[pydantic.types.StrictBool | None, FieldInfo(default=PydanticUndefined, description='If true, only a slice of labels will be returned for samples with multiple labels.', extra={})] = None

  • labels: Annotated[pydantic.types.StrictStr | None, FieldInfo(default=PydanticUndefined, description='Only include samples with a label within the given list of labels, given as a JSON string', extra={})] = None

  • filename: Annotated[pydantic.types.StrictStr | None, FieldInfo(default=PydanticUndefined, description='Only include samples whose filename includes the given filename', extra={})] = None

  • max_length: Annotated[pydantic.types.StrictInt | None, FieldInfo(default=PydanticUndefined, description='Only include samples shorter than the given length, in milliseconds', extra={})] = None

  • min_length: Annotated[pydantic.types.StrictInt | None, FieldInfo(default=PydanticUndefined, description='Only include samples longer than the given length, in milliseconds', extra={})] = None

  • min_frequency: Annotated[float | None, FieldInfo(default=PydanticUndefined, description='Only include samples with higher frequency than given frequency, in hertz', extra={})] = None

  • max_frequency: Annotated[float | None, FieldInfo(default=PydanticUndefined, description='Only include samples with lower frequency than given frequency, in hertz', extra={})] = None

  • signature_validity: Annotated[pydantic.types.StrictStr | None, FieldInfo(default=PydanticUndefined, description='Include samples with either valid or invalid signatures', extra={})] = None

  • min_label: Annotated[float | None, FieldInfo(default=PydanticUndefined, description='Only include samples with a label >= this value', extra={})] = None

  • max_label: Annotated[float | None, FieldInfo(default=PydanticUndefined, description='Only include samples with a label < this value', extra={})] = None

  • search: Annotated[pydantic.types.StrictStr | None, FieldInfo(default=PydanticUndefined, description='Search query', extra={})] = None

  • data_type: Annotated[pydantic.types.StrictStr | None, FieldInfo(default=PydanticUndefined, description='Include only samples with a particular data type', extra={})] = None

  • min_id: Annotated[float | None, FieldInfo(default=PydanticUndefined, description='Include only samples with an ID >= this value', extra={})] = None

  • max_id: Annotated[float | None, FieldInfo(default=PydanticUndefined, description='Include only samples with an ID < this value', extra={})] = None

  • metadata: Annotated[pydantic.types.StrictStr | None, FieldInfo(default=PydanticUndefined, description='Filter samples by metadata key-value pairs, provided as a JSON string. Each filter item in the list is combined using a logical OR. To include samples without any metadata, use: { "no_metadata": true }. ', extra={})] = None

  • min_date: Annotated[datetime.datetime | None, FieldInfo(default=PydanticUndefined, description='Only include samples that where added after the date given', extra={})] = None

  • max_date: Annotated[datetime.datetime | None, FieldInfo(default=PydanticUndefined, description='Only include samples that were added before the date given', extra={})] = None

  • **kwargs

Return

edgeimpulse_api.models.classify_job_response_page.ClassifyJobResponsePage

get_sample_window_from_cache

edgeimpulse_api.api.classify_api.get_sample_window_from_cache(
		self,
		project_id: Annotated[pydantic.types.StrictInt, FieldInfo(default=Ellipsis, description='Project ID', extra={})],
		sample_id: Annotated[pydantic.types.StrictInt, FieldInfo(default=Ellipsis, description='Sample ID', extra={})],
		window_index: Annotated[pydantic.types.StrictInt, FieldInfo(default=Ellipsis, description='Sample window index', extra={})],
		impulse_id: Annotated[pydantic.types.StrictInt | None, FieldInfo(default=PydanticUndefined, description='Impulse ID. If this is unset then the default impulse is used.', extra={})] = None,
		truncate_structured_labels: Annotated[pydantic.types.StrictBool | None, FieldInfo(default=PydanticUndefined, description='If true, only a slice of labels will be returned for samples with multiple labels.', extra={})] = None,
		**kwargs
) ‑> edgeimpulse_api.models.get_sample_response.GetSampleResponse

Get a window of raw sample features from cache, after a live classification job has completed.

Get raw sample features for a particular window. This is only available after a live classification job has completed and raw features have been cached.

Parameters

  • self

  • project_id: Annotated[pydantic.types.StrictInt, FieldInfo(default=Ellipsis, description='Project ID', extra={})]

  • sample_id: Annotated[pydantic.types.StrictInt, FieldInfo(default=Ellipsis, description='Sample ID', extra={})]

  • window_index: Annotated[pydantic.types.StrictInt, FieldInfo(default=Ellipsis, description='Sample window index', extra={})]

  • impulse_id: Annotated[pydantic.types.StrictInt | None, FieldInfo(default=PydanticUndefined, description='Impulse ID. If this is unset then the default impulse is used.', extra={})] = None

  • truncate_structured_labels: Annotated[pydantic.types.StrictBool | None, FieldInfo(default=PydanticUndefined, description='If true, only a slice of labels will be returned for samples with multiple labels.', extra={})] = None

  • **kwargs

Return

edgeimpulse_api.models.get_sample_response.GetSampleResponse

Previousapi packageNextdeployment_api module

Last updated

Was this helpful?