turicreate.one_shot_object_detector.create(data, target, backgrounds=None, batch_size=0, max_iterations=0, verbose=True)

Create a OneShotObjectDetector model. Note: The One Shot Object Detector is currently in beta.

data : SFrame | tc.Image

A single starter image or an SFrame that contains the starter images along with their corresponding labels. These image(s) can be in either RGB or RGBA format. They should not be padded.

target : string

Name of the target (when data is a single image) or the target column name (when data is an SFrame of images).

backgrounds : optional SArray

A list of backgrounds used for synthetic data generation. When set to None, a set of default backgrounds are downloaded and used.

batch_size : int

The number of images per training iteration. If 0, then it will be automatically determined based on resource availability.

max_iterations : int

The number of training iterations. If 0, then it will be automatically be determined based on the amount of data you provide.

verbose : bool optional

If True, print progress updates and model details.


# Train an object detector model
>>> model = turicreate.one_shot_object_detector.create(train_data, label = 'cards')

# Make predictions on the training set and as column to the SFrame
>>> test_data['predictions'] = model.predict(test_data)