Export NeurEco Compression model with the Python API

By default, NeurEco saves models in its binary format .ednn.

A NeurEco embed license allows to export .ednn models to the following formats.

NeurEco Tabular export formats

Format	Precision	Description
FMU	double	The Functional Mock-up Interface (or FMI) defines a standardized interface to be used in computer simulations to develop complex cyber-physical systems. More details are available at these pages: https://fmi-standard.org/, and https://en.wikipedia.org/wiki/Functional_Mock-up_Interface
ONNX	double, float, float16	The Open Neural Network Exchange (ONNX) is an open-source artificial intelligence ecosystem of technology companies and research organizations that establish open standards for representing machine learning algorithms and software tools to promote innovation and collaboration in the AI sector. More details are available at these pages: https://onnx.ai, and https://en.wikipedia.org/wiki/Open_Neural_Network_Exchange
C format	double or float	generates a header file containing a C representation of the neural network inside a single procedure.
VBA format	double or float	generates a visual basic macro representing the neural network for the use from Excel files.

build a Compression model (Build NeurEco Compression model with the Python API) or load an already saved one.

To export the model to the FMU format:

model.export_fmu(fmu_path)

exports a NeurEco model to FMU (Functional Mock-up Interface).

fmu_path

string, required, path where to save the fmu file.

return

int, export_status: 0 if export is successful, other value if not

To export the model to the ONNX format:

model.export_onnx(onnx_file_path, precision="float")

exports a NeurEco Tabular model to a header file.

onnx_file_path

string, required: path where the onnx file will be saved

precision

string, optional, default=”float”: possible values: “float” or “double”, precision of the weights in the onnx file.

return

int, export_status: 0 if export is successful, other value if not

To export the model to the C format (header file):

model.export_c(h_file_path, precision="float")

exports a NeurEco Tabular model to a header file.

h_file_path

string, required, path where the .h file will be saved.

precision

string, optional, default=”float”: possible values: “float” or “double”, precision of the weights in the h file.

return

int, export_status: 0 if export is successful, other value if not

To export the model to the VBA format:

model.export_vba(vba_file_path, precision="float")

exports a NeurEco Tabular model to a VBA file.

vba_file_path

string, required, path where the vba file will be saved.

precision

string, optional, default=”float”: possible values: “float” or “double”, precision of the weights in the h file.

return

int, export_status: 0 if export is successful, other value if not

Any Compression model can be divided in its model_Compressor and model_Decompressor parts via the call to separate_models method, both of them are Regression models:

neurEco_Compressor = Tabular.Regressor()
neurEco_Decompressor = Tabular.Regressor()
separate_status = model.separate_models(neurEco_Compressor, neurEco_Decompressor)

These Regression models can be exported separately (the export functions for a Regression model are the same as for a Compression model, see Export NeurEco Regression model with the Python API)