# TensorFlow Model Conversion

Machine Learning frameworks have specific formats for storing
neural network models. Qualcomm® Neural Processing SDK supports these various models by
converting them to a framework neutral **deep learningcontainer (DLC)** format. The DLC file is used by the Qualcomm® Neural Processing SDK
runtime for execution of the neural network.

A trained TensorFlow model consists of either:

- A frozen TensorFlow model (pb file) OR
- A pair of checkpoint and graph meta files
- A SavedModel directory (Tensorflow 2.x)

The
[snpe-tensorflow-to-dlc](https://docs.qualcomm.com/doc/80-63442-10/topic/SNPE_general_tools.html#snpe-tensorflow-to-dlc)
tool converts a frozen TensorFlow model or a graph meta file
into an equivalent Qualcomm® Neural Processing SDK DLC file. The following command will
convert an Inception v3 TensorFlow model into a Qualcomm® Neural Processing SDK DLC file.

snpe-tensorflow-to-dlc --input_network $SNPE_ROOT/examples/Models/InceptionV3/tensorflow/inception_v3_2016_08_28_frozen.pb \
                           --input_dim input "1,299,299,3" --out_node "InceptionV3/Predictions/Reshape_1" \
                           --output_path inception_v3.dlc
    Copy to clipboard

\* When using converter tools in Windows PowerShell, make sure a virtual environment
with the required packages is activated and execute the converter script via **python**,
as shown in the following example.

(venv-3.10) > python snpe-tensorflow-to-dlc <options>

The Inception v3 model files can be obtained by following the
[Getting Inception v3](https://docs.qualcomm.com/doc/80-63442-10/topic/tutorial_inceptionv3.html) tutorial.

TensorFlow Graph and Qualcomm® Neural Processing SDK Layer Mapping

Qualcomm® Neural Processing SDK, like many other neural network runtime engines, uses layers
as building blocks to define the structure of neural networks.
TensorFlow on the other hand, defines a neural network as a
graph of nodes and a layer is defined as a set of nodes within
the graph.

With this in mind, in order to properly convert a TensorFlow
graph into a Qualcomm® Neural Processing SDK DLC file the following requirements must be
met when defining a TensorFlow graph:

1. All nodes belonging to a layer must be defined in a unique
[TensorFlow
scope.](https://www.tensorflow.org/api_docs/python/tf/name_scope)
2. A node can only belong to a single layer.

More information about graph compatibility can be found in the
[TensorFlow Graph Compatibility](https://docs.qualcomm.com/doc/80-63442-10/topic/tensorflow_graphs.html)
chapter.

Last Published: Jun 04, 2026

[Previous Topic
Model Conversion](https://docs.qualcomm.com/bundle/publicresource/80-63442-10/topics/usergroup3.md) [Next Topic
Tensorflow Graph Compatibility](https://docs.qualcomm.com/bundle/publicresource/80-63442-10/topics/tensorflow_graphs.md)