The ArmnnConverter is a program for converting neural networks from other formats to Arm NN format. Currently the program supports models in Caffe, Onnx, Tensorflow Protocol Buffers and Tensorflow Lite FlatBuffers formats. Run the program with no arguments to see command-line help.

For more information, a list of supported layers, and the networks that have been tested, please visit "Software Tools" -> "Converter" in our doxygen documentation that can be found in the wiki section of our github repository.