add_labels_to_dataframe

edgeimpulse.experimental.util.add_labels_to_dataframe(
		df,
		labels,
		label_col_name='label'
)

Adds labels to a DataFrame based on provided label information.

Parameters

• df

• labels

• label_col_name='label'

convert_json_cbor_to_dataframe

edgeimpulse.experimental.util.convert_json_cbor_to_dataframe(
		data,
		ts_col_name=None
)

Converts JSON CBOR data to a pandas DataFrame.

Parameters

• data

• ts_col_name=None

convert_sample_to_dataframe

edgeimpulse.experimental.util.convert_sample_to_dataframe(
		sample,
		label_col_name: str | None = 'label',
		ts_col_name: str | None = None
)

Converts a sample to a DataFrame and adds labels if provided.

Parameters

• sample

• label_col_name: str | None = 'label'

• ts_col_name: str | None = None

fetch_samples

edgeimpulse.experimental.util.fetch_samples(
		filename: str | None = None,
		category: str | None = None,
		labels: str | None = None,
		max_workers=None
)

Fetch samples based on the provided parameters and stream them by their IDs.

Parameters

• filename: str | None = None

• category: str | None = None

• labels: str | None = None

• max_workers=None

generate_labels_from_dataframe

edgeimpulse.experimental.util.generate_labels_from_dataframe(
		df,
		label_col='label',
		file_name=None
)

Generates structured labels from a DataFrame based on transitions in the specified label column.

This function iterates over the rows of a pandas DataFrame and detects changes in the values of a specified label column. It groups consecutive rows with the same label value, and for each group, it returns a dictionary containing the start index, end index, and the label. Optionally, the result can be returned in a dictionary format, compatible with file saving, including the file name.

Parameters

• df

• label_col='label'

• file_name=None

build

edgeimpulse.experimental.impulse.build(
		deploy_model_type: str | None = None,
		engine: str = 'tflite',
		deploy_target: str = 'zip',
		output_directory: str | None = None,
		api_key: str | None = None,
		timeout_sec: float | None = None
) ‑> _io.BytesIO

Build and download an impulse from Edge Impulse.

Build a model and download it from Edge Impulse. The model can be built for a specific target and engine. The model can be saved to a file if output_directory is provided and the file name will be derived from the deployment target.

Parameters

• deploy_model_type: str | None = None

• engine: str = 'tflite'

• deploy_target: str = 'zip'

• output_directory: str | None = None

• api_key: str | None = None

• timeout_sec: float | None = None

Return

_io.BytesIO

EdgeImpulseApi

class edgeimpulse.experimental.api.EdgeImpulseApi(
		host: str | None = None,
		key: str | None = None,
		key_type: str = 'api'
)

Initialize the Edge Impulse Api.

Parameters

• host: str | None = None

• key: str | None = None

• key_type: str = 'api'

Instance variables

• classify: edgeimpulse_api.api.classify_api.ClassifyApi Classify samples in your project.

• client: edgeimpulse_api.api_client.ApiClient The client used for initializing the apis, use set_client to update the client.

• deployment: edgeimpulse_api.api.deployment_api.DeploymentApi Work with your model deployment targets.

• devices: edgeimpulse_api.api.devices_api.DevicesApi Work with devices in your project.

• dsp: edgeimpulse_api.api.dsp_api.DSPApi Work with (DSP) digital signal processing and feature extraction blocks in your project.

• export: edgeimpulse_api.api.export_api.ExportApi Export your project.

• host: str | None Edge Impulse studio host (defaults to production).

• impulse: edgeimpulse_api.api.impulse_api.ImpulseApi Work and manage your Impulse (on-device feature extraction and classification pipeline).

• jobs: edgeimpulse_api.api.jobs_api.JobsApi Start and manage long running jobs.

• learn: edgeimpulse_api.api.learn_api.LearnApi Work with keras and pretrained models.

• login: edgeimpulse_api.api.login_api.LoginApi Login and authenticate.

• optimization: edgeimpulse_api.api.optimization_api.OptimizationApi Optimize and find a better model with the EON tuner.

• organization_blocks: edgeimpulse_api.api.organization_blocks_api.OrganizationBlocksApi Work with organization blocks.

• organization_create_project: edgeimpulse_api.api.organization_create_project_api.OrganizationCreateProjectApi Automate project creation for organizations.

• organization_data: edgeimpulse_api.api.organization_data_api.OrganizationDataApi Work with organization data.

• organization_data_campaigns: edgeimpulse_api.api.organization_data_campaigns_api.OrganizationDataCampaignsApi Work with organization data campaigns.

• organization_jobs: edgeimpulse_api.api.organization_jobs_api.OrganizationJobsApi Start and manage organization jobs.

• organization_pipelines: edgeimpulse_api.api.organization_pipelines_api.OrganizationPipelinesApi Work with organization pipelines.

• organization_portals: edgeimpulse_api.api.organization_portals_api.OrganizationPortalsApi Create and manage organization portals.

• organizations: edgeimpulse_api.api.organizations_api.OrganizationsApi Work with your organizations.

• performance_calibration: edgeimpulse_api.api.performance_calibration_api.PerformanceCalibrationApi Calibrate your model performance with real world data.

• projects: edgeimpulse_api.api.projects_api.ProjectsApi Create and manage your projects.

• raw_data: edgeimpulse_api.api.raw_data_api.RawDataApi Work with your project data.

• upload_portal: edgeimpulse_api.api.upload_portal_api.UploadPortalApi Create and manage data upload portals.

• user: edgeimpulse_api.api.user_api.UserApi Manage user activation, creation and updates.

Methods

authenticate

edgeimpulse.experimental.api.authenticate(
		self,
		key: str,
		key_type: str = 'api',
		host: str | None = None
) ‑> None

Authenticate against Edge Impulse.

Parameters

• self

• key: str

• key_type: str = 'api'

• host: str | None = None

Return

None

default_project_id

edgeimpulse.experimental.api.default_project_id(
		self
) ‑> int

Get the default project ID from the provided API key.

Returns: int: The project associated with the api key.

Parameters

• self

Return

int

run_organization_job_until_completion

edgeimpulse.experimental.api.run_organization_job_until_completion(
		self,
		organization_id: int,
		job_id: int,
		data_cb=None,
		client=None,
		timeout_sec: int | None = None
) ‑> None

Runs an organization job until completion.

Parameters

• self

• organization_id: int

• job_id: int

• data_cb=None

• client=None

• timeout_sec: int | None = None

Return

None

run_project_job_until_completion

edgeimpulse.experimental.api.run_project_job_until_completion(
		self,
		job_id: int,
		data_cb=None,
		client=None,
		project_id: int | None = None,
		timeout_sec: int | None = None
) ‑> None

Runs a project job until completion.

Parameters

• self

• job_id: int

• data_cb=None

• client=None

• project_id: int | None = None

• timeout_sec: int | None = None

Return

None

set_client

edgeimpulse.experimental.api.set_client(
		self,
		client: edgeimpulse_api.api_client.ApiClient
) ‑> None

Set the API client and initialize the APIs wit that client.

Parameters

• self

• client: edgeimpulse_api.api_client.ApiClient

Return

None

Sample

class edgeimpulse.experimental.data.Sample(
		data: io.BufferedIOBase | _io.StringIO | str,
		filename: str | None = None,
		category: Literal['training', 'testing', 'anomaly', 'split'] | None = 'split',
		label: str | None = None,
		bounding_boxes: List[dict] | None = None,
		metadata: dict | None = None,
		sample_id: int | None = None,
		structured_labels: List[dict] | None = None
)

Wrapper class for sample data, labels, and associated metadata.

Sample data should be contained in a file or file-like object, for example, as the return from open(..., "rb"). The upload_samples() function expects Sample objects as input.

Parameters

• data: io.BufferedIOBase | _io.StringIO | str

• filename: str | None = None

• category: Literal['training', 'testing', 'anomaly', 'split'] | None = 'split'

• label: str | None = None

• bounding_boxes: List[dict] | None = None

• metadata: dict | None = None

• sample_id: int | None = None

• structured_labels: List[dict] | None = None

Class variables

• bounding_boxes: List[dict] | None

• category: Literal['training', 'testing', 'anomaly', 'split'] | None

• data: io.BufferedIOBase | _io.StringIO | str

• filename: str | None

• label: str | None

• metadata: dict | None

• sample_id: int | None

• structured_labels: List[dict] | None

delete_all_samples

edgeimpulse.experimental.data.delete_all_samples(
		category: str | None = None,
		api_key: str | None = None,
		timeout_sec: float | None = None
) ‑> edgeimpulse_api.models.generic_api_response.GenericApiResponse | None

Delete all samples in a given category.

If category is set to None, all samples in the project are deleted.

Parameters

• category: str | None = None

• api_key: str | None = None

• timeout_sec: float | None = None

Return

edgeimpulse_api.models.generic_api_response.GenericApiResponse | None

delete_sample_by_id

edgeimpulse.experimental.data.delete_sample_by_id(
		sample_id: int,
		api_key: str | None = None,
		timeout_sec: float | None = None
) ‑> edgeimpulse_api.models.generic_api_response.GenericApiResponse | None

Delete a particular sample from a project given the sample ID.

Parameters

• sample_id: int

• api_key: str | None = None

• timeout_sec: float | None = None

Return

edgeimpulse_api.models.generic_api_response.GenericApiResponse | None

delete_samples_by_filename

edgeimpulse.experimental.data.delete_samples_by_filename(
		filename: str,
		category: str | None = None,
		api_key: str | None = None,
		timeout_sec: float | None = None
) ‑> Tuple[Any | None, ...]

Delete any samples from an Edge Impulse project that match the given filename.

Note: the filename argument must not include the original extension. For example, if you uploaded a file named my-image.01.png, you must provide the filename as my-image.01.

Parameters

• filename: str

• category: str | None = None

• api_key: str | None = None

• timeout_sec: float | None = None

Return

Tuple[Any | None, ...]

download_samples_by_ids

edgeimpulse.experimental.data.download_samples_by_ids(
		sample_ids: int | List[int],
		api_key: str | None = None,
		timeout_sec: float | None = None,
		max_workers: int | None = None,
		show_progress: bool | None = False,
		pool_maxsize: int | None = 20,
		pool_connections: int | None = 20
) ‑> List[edgeimpulse.data.sample_type.Sample]

Download samples by their associated IDs from an Edge Impulse project.

Downloaded sample data is returned as a DownloadSample object, which contains the raw data in a BytesIO object along with associated metadata.

Important! All time series data is returned as a JSON file (in BytesIO format) with a timestamp column. This includes files originally uploaded as CSV, JSON, and CBOR. Edge Impulse Studio removes the timestamp column from any uploaded CSV files and computes an estimated sample rate. The timestamps are computed based on the sample rate, will always start at 0, and will be in milliseconds. These timestamps may not be the same as the original timestamps in the uploaded file.

Parameters

• sample_ids: int | List[int]

• api_key: str | None = None

• timeout_sec: float | None = None

• max_workers: int | None = None

• show_progress: bool | None = False

• pool_maxsize: int | None = 20

• pool_connections: int | None = 20

Return

List[edgeimpulse.data.sample_type.Sample]

get_filename_by_id

edgeimpulse.experimental.data.get_filename_by_id(
		sample_id: int,
		api_key: str | None = None,
		timeout_sec: float | None = None
) ‑> str | None

Given an ID for a sample in a project, return the filename associated with that sample.

Note that while multiple samples can have the same filename, each sample has a unique sample ID that is provided by Studio when the sample is uploaded.

Parameters

• sample_id: int

• api_key: str | None = None

• timeout_sec: float | None = None

Return

str | None

get_sample_ids

edgeimpulse.experimental.data.get_sample_ids(
		filename: str | None = None,
		category: str | None = None,
		labels: str | None = None,
		api_key: str | None = None,
		num_workers: int | None = 4,
		timeout_sec: float | None = None
) ‑> List[edgeimpulse.data.sample_type.SampleInfo]

Get the sample IDs and filenames for all samples in a project, filtered by category, labels, or filename.

Note that filenames are given by the root of the filename when uploaded. For example, if you upload my-image.01.png, it will be stored in your project with a hash such as my-image.01.png.4f262n1b.json. To find the ID(s) that match this sample, you must provide the argument filename=my-image.01. Notice the lack of extension and hash.

Because of the potential for multiple samples (i.e., different sample IDs) with the same filename, we recommend providing unique filenames for your samples when uploading.

Parameters

• filename: str | None = None

• category: str | None = None

• labels: str | None = None

• api_key: str | None = None

• num_workers: int | None = 4

• timeout_sec: float | None = None

Return

List[edgeimpulse.data.sample_type.SampleInfo]

infer_category_and_label_from_filename

edgeimpulse.experimental.data.infer_category_and_label_from_filename(
		sample: edgeimpulse.data.sample_type.Sample,
		file: str
) ‑> None

Extract label and category information from the filename and assigns them to the sample object.

Files should look like this my-dataset/training/wave.1.cbor where wave is the label and training is the category. It checks if there is training, testing or anomaly in the filename to determine the sample category.

Parameters

• sample: edgeimpulse.data.sample_type.Sample

• file: str

Return

None

numpy_timeseries_to_sample

edgeimpulse.experimental.data.numpy_timeseries_to_sample(
		values,
		sensors: List[edgeimpulse.data.sample_type.Sensor],
		sample_rate_ms: int
) ‑> edgeimpulse.data.sample_type.Sample

Convert numpy values to a sample that can be uploaded to Edge Impulse.

Parameters

• values

• sensors: List[edgeimpulse.data.sample_type.Sensor]

• sample_rate_ms: int

Return

edgeimpulse.data.sample_type.Sample

pandas_dataframe_to_sample

edgeimpulse.experimental.data.pandas_dataframe_to_sample(
		df,
		sample_rate_ms: int | None = None,
		label: str | None = None,
		filename: str | None = None,
		axis_columns: List[str] | None = None,
		metadata: dict | None = None,
		label_col: str | None = None,
		category: Literal['training', 'testing', 'split'] = 'split'
) ‑> edgeimpulse.data.sample_type.Sample

Convert a dataframe to a single sample. Can handle both timeseries and non-timeseries data.

In order to be inferred as timeseries it must have:

• More than one row

• A sample rate or an index from which the sample rate can be inferred

  • Therefore must be monotonically increasing

  • And int or a date

Parameters

• df

• sample_rate_ms: int | None = None

• label: str | None = None

• filename: str | None = None

• axis_columns: List[str] | None = None

• metadata: dict | None = None

• label_col: str | None = None

• category: Literal['training', 'testing', 'split'] = 'split'

Return

edgeimpulse.data.sample_type.Sample

stream_samples_by_ids

edgeimpulse.experimental.data.stream_samples_by_ids(
		sample_ids: int | Sequence[int],
		api_key: str | None = None,
		timeout_sec: float | None = None,
		max_workers: int | None = None,
		show_progress: bool | None = False,
		pool_maxsize: int | None = 20,
		pool_connections: int | None = 20
) ‑> Generator[edgeimpulse.data.sample_type.Sample, None, None]

Download samples by their associated IDs from an Edge Impulse project.

Parameters

• sample_ids: int | Sequence[int]

• api_key: str | None = None

• timeout_sec: float | None = None

• max_workers: int | None = None

• show_progress: bool | None = False

• pool_maxsize: int | None = 20

• pool_connections: int | None = 20

Return

Generator[edgeimpulse.data.sample_type.Sample, None, None]

upload_directory

edgeimpulse.experimental.data.upload_directory(
		directory: str,
		category: str | None = None,
		label: str | None = None,
		metadata: dict | None = None,
		transform: <built-in function callable> | None = None,
		allow_duplicates: bool | None = False,
		show_progress: bool | None = False,
		batch_size: int | None = 1024
) ‑> edgeimpulse.data.sample_type.UploadSamplesResponse

Upload a directory of files to Edge Impulse.

Tries to autodetect whether it's an Edge Impulse exported dataset, or a standard directory. The files can be in CBOR, JSON, image, or WAV file formats. You can read more about the different file formats accepted by the Edge Impulse ingestion service here:

https://docs.edgeimpulse.com/reference/ingestion-api

Parameters

• directory: str

• category: str | None = None

• label: str | None = None

• metadata: dict | None = None

• transform: <built-in function callable> | None = None

• allow_duplicates: bool | None = False

• show_progress: bool | None = False

• batch_size: int | None = 1024

Return

edgeimpulse.data.sample_type.UploadSamplesResponse

upload_exported_dataset

edgeimpulse.experimental.data.upload_exported_dataset(
		directory: str,
		transform: <built-in function callable> | None = None,
		allow_duplicates: bool | None = False,
		show_progress: bool | None = False,
		batch_size: int | None = 1024
) ‑> edgeimpulse.data.sample_type.UploadSamplesResponse

Upload samples from a downloaded Edge Impulse dataset and preserve the info.labels information.

Use this when you've exported your data in the studio, via the export functionality.

Parameters

• directory: str

• transform: <built-in function callable> | None = None

• allow_duplicates: bool | None = False

• show_progress: bool | None = False

• batch_size: int | None = 1024

Return

edgeimpulse.data.sample_type.UploadSamplesResponse

upload_numpy

edgeimpulse.experimental.data.upload_numpy(
		data,
		labels: List[str],
		sensors: List[edgeimpulse.data.sample_type.Sensor],
		sample_rate_ms: int,
		metadata: dict | None = None,
		category: Literal['training', 'testing', 'split', 'anomaly'] = 'split'
) ‑> edgeimpulse.data.sample_type.UploadSamplesResponse

Upload numpy arrays as timeseries using the Edge Impulse data acquisition format.

Parameters

• data

• labels: List[str]

• sensors: List[edgeimpulse.data.sample_type.Sensor]

• sample_rate_ms: int

• metadata: dict | None = None

• category: Literal['training', 'testing', 'split', 'anomaly'] = 'split'

Return

edgeimpulse.data.sample_type.UploadSamplesResponse

upload_pandas_dataframe

edgeimpulse.experimental.data.upload_pandas_dataframe(
		df,
		feature_cols: List[str],
		label_col: str | None = None,
		category_col: str | None = None,
		metadata_cols: List[str] | None = None
) ‑> edgeimpulse.data.sample_type.UploadSamplesResponse

Upload non-timeseries data to Edge Impulse where each dataframe row becomes a sample.

Parameters

• df

• feature_cols: List[str]

• label_col: str | None = None

• category_col: str | None = None

• metadata_cols: List[str] | None = None

Return

edgeimpulse.data.sample_type.UploadSamplesResponse

upload_pandas_dataframe_wide

edgeimpulse.experimental.data.upload_pandas_dataframe_wide(
		df,
		sample_rate_ms: int,
		data_col_start: int | None = None,
		label_col: str | None = None,
		category_col: str | None = None,
		metadata_cols: List[str] | None = None,
		data_col_length: int | None = None,
		data_axis_cols: List[str] | None = None
) ‑> edgeimpulse.data.sample_type.UploadSamplesResponse

Upload a dataframe to Edge Impulse where each column represents a value in the timeseries data and the rows become the individual samples.

Parameters

• df

• sample_rate_ms: int

• data_col_start: int | None = None

• label_col: str | None = None

• category_col: str | None = None

• metadata_cols: List[str] | None = None

• data_col_length: int | None = None

• data_axis_cols: List[str] | None = None

Return

edgeimpulse.data.sample_type.UploadSamplesResponse

upload_pandas_dataframe_with_group

edgeimpulse.experimental.data.upload_pandas_dataframe_with_group(
		df,
		timestamp_col: str,
		group_by: str,
		feature_cols: List[str],
		label_col: str | None = None,
		category_col: str | None = None,
		metadata_cols: List[str] | None = None
) ‑> edgeimpulse.data.sample_type.UploadSamplesResponse

Upload a dataframe where the rows contain multiple samples and timeseries data for those samples.

It uses a group_by in order to detect what timeseries value belongs to which sample.

Parameters

• df

• timestamp_col: str

• group_by: str

• feature_cols: List[str]

• label_col: str | None = None

• category_col: str | None = None

• metadata_cols: List[str] | None = None

Return

edgeimpulse.data.sample_type.UploadSamplesResponse

upload_pandas_sample

edgeimpulse.experimental.data.upload_pandas_sample(
		df,
		label: str | None = None,
		sample_rate_ms: int | None = None,
		filename: str | None = None,
		axis_columns: List[str] | None = None,
		metadata: dict | None = None,
		label_col: str | None = None,
		category: Literal['training', 'testing', 'split'] = 'split'
) ‑> edgeimpulse.data.sample_type.UploadSamplesResponse

Upload a single dataframe sample.

Upload a single dataframe sample to Edge Impulse.

Parameters

• df

• label: str | None = None

• sample_rate_ms: int | None = None

• filename: str | None = None

• axis_columns: List[str] | None = None

• metadata: dict | None = None

• label_col: str | None = None

• category: Literal['training', 'testing', 'split'] = 'split'

Return

edgeimpulse.data.sample_type.UploadSamplesResponse

upload_plain_directory

edgeimpulse.experimental.data.upload_plain_directory(
		directory: str,
		category: str | None = None,
		label: str | None = None,
		metadata: dict | None = None,
		transform: <built-in function callable> | None = None,
		allow_duplicates: bool | None = False,
		show_progress: bool | None = False,
		batch_size: int | None = 1024
) ‑> edgeimpulse.data.sample_type.UploadSamplesResponse

Upload a directory of files to Edge Impulse.

The samples can be in CBOR, JSON, image, or WAV file formats.

Parameters

• directory: str

• category: str | None = None

• label: str | None = None

• metadata: dict | None = None

• transform: <built-in function callable> | None = None

• allow_duplicates: bool | None = False

• show_progress: bool | None = False

• batch_size: int | None = 1024

Return

edgeimpulse.data.sample_type.UploadSamplesResponse

upload_samples

edgeimpulse.experimental.data.upload_samples(
		samples: edgeimpulse.data.sample_type.Sample | List[edgeimpulse.data.sample_type.Sample],
		allow_duplicates: bool | None = False,
		api_key: str | None = None,
		timeout_sec: float | None = None,
		max_workers: int | None = None,
		show_progress: bool | None = False,
		pool_maxsize: int | None = 20,
		pool_connections: int | None = 20
) ‑> edgeimpulse.data.sample_type.UploadSamplesResponse

Upload one or more samples to an Edge Impulse project using the ingestion service.

Each sample must be wrapped in a Sample object, which contains metadata about that sample. Give this function a single Sample or a List of Sample objects to upload to your project. The data field of the Sample must be a raw binary stream, such as a BufferedIOBase object (which you can create with the open(..., "rb") function).

Parameters

• samples: edgeimpulse.data.sample_type.Sample | List[edgeimpulse.data.sample_type.Sample]

• allow_duplicates: bool | None = False

• api_key: str | None = None

• timeout_sec: float | None = None

• max_workers: int | None = None

• show_progress: bool | None = False

• pool_maxsize: int | None = 20

• pool_connections: int | None = 20

Return

edgeimpulse.data.sample_type.UploadSamplesResponse

check_tuner

edgeimpulse.experimental.tuner.check_tuner(
		timeout_sec: int | None = None,
		wait_for_completion: bool = True
) ‑> edgeimpulse_api.models.optimize_state_response.OptimizeStateResponse

Check the current state of the tuner and optionally waits until the tuner has completed.

Parameters

• timeout_sec: int | None = None

• wait_for_completion: bool = True

Return

edgeimpulse_api.models.optimize_state_response.OptimizeStateResponse

get_tuner_run_state

edgeimpulse.experimental.tuner.get_tuner_run_state(
		tuner_coordinator_job_id: int
) ‑> edgeimpulse_api.models.optimize_state_response.OptimizeStateResponse

Retrieve the current state of the tuner run.

Returns: OptimizeStateResponse: The OptimizeStateResponse object representing the current Tuner state.

Parameters

• tuner_coordinator_job_id: int

Return

edgeimpulse_api.models.optimize_state_response.OptimizeStateResponse

list_tuner_runs

edgeimpulse.experimental.tuner.list_tuner_runs(
		
) ‑> edgeimpulse_api.models.list_tuner_runs_response.ListTunerRunsResponse

List the tuner runs that have been done in the current project.

Returns: ListTunerRunsResponse: An object containing all the tuner runs

Return

edgeimpulse_api.models.list_tuner_runs_response.ListTunerRunsResponse

print_tuner_coordinator_logs

edgeimpulse.experimental.tuner.print_tuner_coordinator_logs(
		limit: int = 500
) ‑> None

Retrieve and print logs for the tuner coordinator job.

Returns: None

Parameters

• limit: int = 500

Return

None

print_tuner_job_logs

edgeimpulse.experimental.tuner.print_tuner_job_logs(
		limit: int = 500
) ‑> None

Retrieve and print logs for the tuner job.

Returns: None

Parameters

• limit: int = 500

Return

None

set_impulse_from_trial

edgeimpulse.experimental.tuner.set_impulse_from_trial(
		trial_id: str,
		timeout_sec: float | None = None,
		wait_for_completion: bool | None = True
) ‑> edgeimpulse_api.models.start_job_response.StartJobResponse

Replace the current Impulse configuration with one found in a trial fromm the tuner.

Parameters

• trial_id: str

• timeout_sec: float | None = None

• wait_for_completion: bool | None = True

Return

edgeimpulse_api.models.start_job_response.StartJobResponse

start_custom_tuner

edgeimpulse.experimental.tuner.start_custom_tuner(
		config: edgeimpulse_api.models.optimize_config.OptimizeConfig
) ‑> edgeimpulse_api.models.start_job_response.StartJobResponse

Start a tuner job with custom configuration.

Parameters

• config: edgeimpulse_api.models.optimize_config.OptimizeConfig

Return

edgeimpulse_api.models.start_job_response.StartJobResponse

start_tuner

edgeimpulse.experimental.tuner.start_tuner(
		space: List[edgeimpulse_api.models.tuner_space_impulse.TunerSpaceImpulse],
		target_device: str,
		target_latency: int,
		tuning_max_trials: int | None = None,
		name: str | None = None
) ‑> edgeimpulse_api.models.start_job_response.StartJobResponse

Start the EON tuner with default settings. Use start_custom_tuner to specify config.

Parameters

• space: List[edgeimpulse_api.models.tuner_space_impulse.TunerSpaceImpulse]

• target_device: str

• target_latency: int

• tuning_max_trials: int | None = None

• name: str | None = None

Return

edgeimpulse_api.models.start_job_response.StartJobResponse

tuner_report_as_df

edgeimpulse.experimental.tuner.tuner_report_as_df(
		state: edgeimpulse_api.models.optimize_state_response.OptimizeStateResponse
)

Get a tuner trial report dataframe with model metrics and block configuration.

This method needs pandas to be installed.

Generate a dataframe on the tuner trials including used input, model, learn block configuration and model validation metrics.

Parameters

• state: edgeimpulse_api.models.optimize_state_response.OptimizeStateResponse

Submodules

• edgeimpulse.experimental.api

• edgeimpulse.experimental.data

• edgeimpulse.experimental.impulse

• edgeimpulse.experimental.tuner

• edgeimpulse.experimental.util

EdgeImpulseApi

class edgeimpulse.experimental.EdgeImpulseApi(
		host: str | None = None,
		key: str | None = None,
		key_type: str = 'api'
)

Initialize the Edge Impulse Api.

Parameters

• host: str | None = None

• key: str | None = None

• key_type: str = 'api'

Instance variables

• classify: edgeimpulse_api.api.classify_api.ClassifyApi Classify samples in your project.

• client: edgeimpulse_api.api_client.ApiClient The client used for initializing the apis, use set_client to update the client.

• deployment: edgeimpulse_api.api.deployment_api.DeploymentApi Work with your model deployment targets.

• devices: edgeimpulse_api.api.devices_api.DevicesApi Work with devices in your project.

• dsp: edgeimpulse_api.api.dsp_api.DSPApi Work with (DSP) digital signal processing and feature extraction blocks in your project.

• export: edgeimpulse_api.api.export_api.ExportApi Export your project.

• host: str | None Edge Impulse studio host (defaults to production).

• impulse: edgeimpulse_api.api.impulse_api.ImpulseApi Work and manage your Impulse (on-device feature extraction and classification pipeline).

• jobs: edgeimpulse_api.api.jobs_api.JobsApi Start and manage long running jobs.

• learn: edgeimpulse_api.api.learn_api.LearnApi Work with keras and pretrained models.

• login: edgeimpulse_api.api.login_api.LoginApi Login and authenticate.

• optimization: edgeimpulse_api.api.optimization_api.OptimizationApi Optimize and find a better model with the EON tuner.

• organization_blocks: edgeimpulse_api.api.organization_blocks_api.OrganizationBlocksApi Work with organization blocks.

• organization_create_project: edgeimpulse_api.api.organization_create_project_api.OrganizationCreateProjectApi Automate project creation for organizations.

• organization_data: edgeimpulse_api.api.organization_data_api.OrganizationDataApi Work with organization data.

• organization_data_campaigns: edgeimpulse_api.api.organization_data_campaigns_api.OrganizationDataCampaignsApi Work with organization data campaigns.

• organization_jobs: edgeimpulse_api.api.organization_jobs_api.OrganizationJobsApi Start and manage organization jobs.

• organization_pipelines: edgeimpulse_api.api.organization_pipelines_api.OrganizationPipelinesApi Work with organization pipelines.

• organization_portals: edgeimpulse_api.api.organization_portals_api.OrganizationPortalsApi Create and manage organization portals.

• organizations: edgeimpulse_api.api.organizations_api.OrganizationsApi Work with your organizations.

• performance_calibration: edgeimpulse_api.api.performance_calibration_api.PerformanceCalibrationApi Calibrate your model performance with real world data.

• projects: edgeimpulse_api.api.projects_api.ProjectsApi Create and manage your projects.

• raw_data: edgeimpulse_api.api.raw_data_api.RawDataApi Work with your project data.

• upload_portal: edgeimpulse_api.api.upload_portal_api.UploadPortalApi Create and manage data upload portals.

• user: edgeimpulse_api.api.user_api.UserApi Manage user activation, creation and updates.

Methods

authenticate

edgeimpulse.experimental.authenticate(
		self,
		key: str,
		key_type: str = 'api',
		host: str | None = None
) ‑> None

Authenticate against Edge Impulse.

Parameters

• self

• key: str

• key_type: str = 'api'

• host: str | None = None

Return

None

default_project_id

edgeimpulse.experimental.default_project_id(
		self
) ‑> int

Get the default project ID from the provided API key.

Returns: int: The project associated with the api key.

Parameters

• self

Return

int

run_organization_job_until_completion

edgeimpulse.experimental.run_organization_job_until_completion(
		self,
		organization_id: int,
		job_id: int,
		data_cb=None,
		client=None,
		timeout_sec: int | None = None
) ‑> None

Runs an organization job until completion.

Parameters

• self

• organization_id: int

• job_id: int

• data_cb=None

• client=None

• timeout_sec: int | None = None

Return

None

run_project_job_until_completion

edgeimpulse.experimental.run_project_job_until_completion(
		self,
		job_id: int,
		data_cb=None,
		client=None,
		project_id: int | None = None,
		timeout_sec: int | None = None
) ‑> None

Runs a project job until completion.

Parameters

• self

• job_id: int

• data_cb=None

• client=None

• project_id: int | None = None

• timeout_sec: int | None = None

Return

None

set_client

edgeimpulse.experimental.set_client(
		self,
		client: edgeimpulse_api.api_client.ApiClient
) ‑> None

Set the API client and initialize the APIs wit that client.

Parameters

• self

• client: edgeimpulse_api.api_client.ApiClient

Return

None