dlpy.model.Model.from_keras_model

classmethod Model.from_keras_model(conn, keras_model, output_model_table=None, offsets=None, std=None, scale=1.0, max_num_frames=- 1, include_weights=False, input_weights_file=None, verbose=False)

Generate a model object from a Keras model object

Parameters

connCAS

The CAS connection object.

keras_modelkeras_model object

Specifies the keras model to be converted.

output_model_tablestring or dict or CAS table, optional

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

offsetslist, optional

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

stdlist or None

The pixel values of the input data are divided by these values, used if the data is an image.

scalefloat, optional

Specifies the scaling factor to apply to each image.

max_num_framesint, optional

Maximum number of frames for sequence processing.

include_weightsbool, optional

Specifies whether to load the weights of the keras model. Default: True

input_weights_filestring, optional

A fully specified client side path to the HDF5 file that stores the keras model weights. Only effective when include_weights=True. If None is given, the current weights in the keras model will be used. Default: None

verboseboolean optional

Specifies whether to print warning messages and debugging information Default: False

Returns

Model

booleanuse GPU