The quantized model is tensorflow protobuf format by default. If you want to get a ONNX format
model, just add output_format argument to the
vai_q_tensorflow command.
$vai_q_tensorflow quantize \
--input_frozen_graph frozen_graph.pb \
--input_nodes ${input_nodes} \
--input_shapes ${input_shapes} \
--output_nodes ${output_nodes} \
--input_fn input_fn \
--output_format onnx \
[options]
- output_format
- Indicates what format to save the quantized model, 'pb' for saving tensorflow frozen pb, 'onnx' for saving onnx model. The default value is 'pb'.