dlpy.model.Model.from_onnx_model

classmethod Model.from_onnx_model(conn, onnx_model, output_model_table=None, offsets=None, scale=None, std=None, norm_stds=None, output_layer=None)

Generate a Model object from ONNX model.

Parameters

connCAS

Specifies the CAS connection object.

onnx_modelModelProto

Specifies the ONNX model.

output_model_tablestring or dict or CAS table, optional

Specifies the CAS table to store the deep learning model. Default: None

offsetsint-list, optional

Specifies the values to be subtracted from the pixel values of the input data, used if the data is an image.

scalefloat, optional

Specifies the scaling factor to apply to each image.

stdstring, optional

Specifies how to standardize the variables in the input layer. Valid Values: MIDRANGE, NONE, STD

norm_stdsfloat-list, optional

Specifies a standard deviation for each channel in the input data. The final input data is normalized with specified means and standard deviations.

output_layerLayer object, optional

Specifies the output layer of the model. If no output layer is specified, the last layer is automatically set as OutputLayer with SOFTMAX activation.

Returns

Model