Overview Before you begin Setup and download libraries Build the Arm Compute Library Build the Boost Library Build the Google protobuf Library Generate the TensorFlow protobuf Library Build the Google FlatBuffers library Build Arm NN Test your build Next steps
Single Page Download PDF

Generate the TensorFlow protobuf library

Use the script provided by Arm NN to generate C++ sources and headers using the protobuf compiler, to provide the protobuf code that can interpret the TensorFlow data format.

To do this, change to the TensorFlow directory and enter:

<Arm NN directory>/armnn/scripts/generate_tensorflow_protobuf.sh <OUTPUT_DIR> <the protobuf install directory>

For example: 

$ cd $BASEDIR/tensorflow
$ ../armnn/scripts/generate_tensorflow_protobuf.sh ../tensorflow-protobuf ../protobuf-host

You can also use the code to interpret the TensorFlow Lite format, by using the example:

$ mkdir tflite
$ cd tflite
$ cp $BASEDIR/tensorflow/tensorflow/lite/schema/schema.fbs .
$ $BASEDIR/flatbuffers-1.12.0/build/flatc -c --gen-object-api --reflect-types --reflect-names schema.fbs
Previous Next