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 about the layers that are supported, see TensorFlowSupport.md, TensorFlowLiteSupport.md, OnnxSupport.md, CaffeSupport.md and SerializerSupport.md.