# Preparing a model with UDO

This section talks about the steps required to convert a
framework model with user defined operations (UDO).

Converting a network model with UDO into DLC

**snpe-<framework>-to-dlc** tools support UDO functionality by
accepting configuration file(s) with the option
–udo\_config\_paths. For input UDO config file specifications,
see Defining a UDO.
Currently UDO functionality is supported on TensorFlow
and ONNX models.

**Note:** Any modifications in the UDO configuration file
should be followed up with re-generation of DLCs to reflect the
changes.

**Converting Tensorflow model with UDO to DLC**

The following syntax showcases the way TensorFlow models can be
converted using UDO:

snpe-tensorflow-to-dlc -i <input-tensorflow-model>
                           -d <input-name> <input-dim>
                           --out_node <output-node-name>
                           --udo_config_paths <input-model.json>
                           -o <output-model.dlc>
    Copy to clipboard

where the option –udo\_config\_paths allows users to specify the
UDO configuration file to be used in the conversion.

See snpe-tensorflow-to-dlc and
TensorFlow Model Conversion for further details.

**Converting ONNX model with UDO to DLC**

The following syntax showcases the way ONNX models can be
converted using UDO:

snpe-onnx-to-dlc -i <input-onnx-model>
                     --udo_config_paths <input-model.json>
                     -o <output-model.dlc>
    Copy to clipboard

where the option –udo\_config\_paths allows users to specify the
UDO configuration file to be used in the conversion.

See snpe-onnx-to-dlc and
ONNX Model Conversion for further details.

Quantizing a DLC with UDO

Additionally, users may want to quantize converted models
having UDOs to run on fixed-point runtimes. Qualcomm® Neural Processing SDK provides
the tool
snpe-dlc-quantize for
this purpose. This is an offline tool that can be run on the
host x86 platform. Since it runs inferences with a
representative data-set in order to determine quantization
ranges for all layers in the network *including UDOs*, users
will need to provide a UDO package containing CPU reference
implementation to the tool. Refer to Creating a UDO
Package and Compiling a UDO
package for further
instructions on creating such a package for the x86 platform.

The following syntax showcases the way DLCs with UDOs can be
quantized with snpe-dlc-quantize:

snpe-dlc-quantize --input_dlc <model.dlc>
                      --input_list <input-list.txt>
                      --udo_package_path <udo-registration-lib>
                      --output_dlc <quantized-model.dlc>
    Copy to clipboard

where the option –udo\_package\_path allows users to specify the
absolute path to the UDO registration library.
LD\_LIBRARY\_PATH must also be updated to include the runtime-specific artifacts generated from package
compilation during x86 Host Compilation .

**Note:** If your UDO contains static inputs or parameters, you
need to handle both floating-point and fixed-point data types
in CPU reference implementation. Refer to provided example
$SNPE\_ROOT/examples/SNPE/NativeCpp/UdoExample/Conv2D/src/CPU/Conv.cpp
for details.

Last Published: Oct 02, 2025

Previous Topic
 
Compiling a Windows UDO for Registration Library and CPU Implementation Library (Optional) on Devices Next Topic

Running a model with UDO