What is the TensorFlow C++ equivalent of argmax (axis=-1)

Question

I am predicting pb graph output in TensorFlow C++. The session->Run works fine and it gives a list of float values as output

load_graph_status = session->Run(inputs, { output_layer_name }, {}, &outputs);

I have done similar prediction in Python where I used

output = outputs.argmax(axis=-1)

I couldn't find the equivalent of this in C++? There is a tensorflow::ops::argmax in TensorFlow C++ documentation. But I couldn't figure out how to use it.

Answer 1

To answer my own question, there is no direct method in C++ that does this job. The work around is to fetch and store each output value iteratively and get the maximum of the list.