Wrapper for Cloud API Models¶

Provides class to wrap existing models in different frameworks so that they provide a unified API to the benchmarks.

`AipModel`	Base class for models hosted on Baidu AIP platform.
`AipAntiPornModel`	Create a `Model` instance from an AipAntiPorn model.
`GoogleCloudModel`	Base class for models in Google Cloud.
`GoogleSafeSearchModel`	Create a :class: Model instance from a GoogleSafeSearchModel model.
`GoogleObjectDetectionModel`	Create a :class: Model instance from a GoogleObjectDetectionModel model.

class perceptron.models.classification.AipModel(credential, bounds=(0, 255), channel_axis=3, preprocessing=(0, 1))[source]¶

Base class for models hosted on Baidu AIP platform.

Parameters:

credential : tuple: Tuple of (appId, apiKey, secretKey) for using AIP API.
bounds : tuple: Tuple of lower and upper bound for the pixel values, usually (0, 1) or (0, 255).
channel_axis : int: The index of the axis that represents color channels.
preprocessing: 2-element tuple with floats or numpy arrays: Elementwises preprocessing of input; we first substract the first element of preprocessing from the input and then divide the input by the second element.

class perceptron.models.classification.AipAntiPornModel(credential, bounds=(0, 255), channel_axis=3, preprocessing=(0, 1))[source]¶

Create a Model instance from an AipAntiPorn model.

Parameters:

credential : tuple: Tuple of (appId, apiKey, secretKey) for using AIP API.
bounds : tuple: Tuple of lower and upper bound for the pixel values, usually (0, 1) or (0, 255).
channel_axis : int: The index of the axis that represents color channels.
preprocessing: 2-element tuple with floats or numpy arrays: Elementwises preprocessing of input; we first substract the first element of preprocessing from the input and then divide the input by the second element.

predictions(self, image)[source]¶

Get prediction for input image

Parameters:	image : numpy.ndarray The input image in [h, n, c] ndarry format.
Returns:	list List of anitporn prediction resutls. Each element is a dictionary containing: {‘class_name’, ‘probability’}

class perceptron.models.classification.GoogleCloudModel(bounds=(0, 255), channel_axis=3, preprocessing=(0, 1))[source]¶

Base class for models in Google Cloud.

Parameters:	bounds : tuple Tuple of lower and upper bound for the pixel values, usually (0, 1) or (0, 255). channel_axis : int The index of the axis that represents color channels. preprocessing: 2-element tuple with floats or numpy arrays Elementwises preprocessing of input; we first substract the first element of preprocessing from the input and then divide the input by the second element.

Notes

To use google cloud vision models, you need to install its package pip instlal –upgrade google-cloud-vision.

class perceptron.models.classification.GoogleSafeSearchModel(bounds=(0, 255), channel_axis=3, preprocessing=(0, 1))[source]¶

Create a :class: Model instance from a GoogleSafeSearchModel model.

Parameters:	bounds : tuple Tuple of lower and upper bound for the pixel values, usually (0, 1) or (0, 255). channel_axis : int The index of the axis that represents color channels. preprocessing: 2-element tuple with floats or numpy arrays Elementwises preprocessing of input; we first substract the first element of preprocessing from the input and then divide the input by the second element.

predictions(self, image)[source]¶

Get prediction for input image.

Parameters:	image : numpy.ndarray The input image in [h, n, c] ndarry format.
Returns:	list List of prediction resutls. Each element is a dictionary containing: {‘adult’, ‘medical’, ‘racy’, ‘spoof’, ‘violence’}.

class perceptron.models.classification.GoogleObjectDetectionModel(bounds=(0, 255), channel_axis=3, preprocessing=(0, 1))[source]¶

Create a :class: Model instance from a GoogleObjectDetectionModel model.

Parameters:	bounds : tuple Tuple of lower and upper bound for the pixel values, usually (0, 1) or (0, 255). channel_axis : int The index of the axis that represents color channels. preprocessing: 2-element tuple with floats or numpy arrays Elementwises preprocessing of input; we first substract the first element of preprocessing from the input and then divide the input by the second element.

predictions(self, image)[source]¶

Get detection result for input image.

Parameters:	image : numpy.ndarray The input image in [h, n, c] ndarry format.
Returns:	list List of batch prediction resutls. Each element is a dictionary containing: {‘name’, ‘score’, ‘mid’, ‘bounding_poly’}.