prediction module

class prediction.Prediction(client, uuid)

Bases: object

property current_results

ids of current results

delete()

Delete this prediction job

download(save_dir=None)

Download the prediction results as tar.gz archive.

Args:

save_dir: directory to save the results.

Returns:

get_results(sample_ids)
Args:

sample_ids (list): id(s) of the sample(s) to retrieve

Returns:

AttrDict of numpy array: sample (including ground truth if present), and prediction

property info

Prediction job info

restart()

Restart this prediction job

stop()

Stop this prediction job

static submit(client, trained_model_id, dataset_id)

Submit a new batch prediction job

Args:

client: API client trained_model_id: trained model id to use dataset_id: dataset id to use

Returns:

Prediction