terminate called after throwing an instance of 'Ort::Exception' what(): Invalid input name: serving_default_input_1:0

[zainali-AT]

Describe the issue

Attempting to run inference using the ORT C++ API (TensorRT EP). The equivalent Python pipeline works, but for some reason the retrieved input name does not match the actual ONNX model's input name (input_1) - as verified by using Netron.

terminate called after throwing an instance of 'Ort::Exception'
  what():  Invalid input name: serving_default_input_1:0

To reproduce

// Get input count
    size_t input_count = session.GetInputCount();
    for (size_t i = 0; i < input_count; ++i) {
        auto input_name_ptr = session.GetInputNameAllocated(i, allocator);
        // std::string input_name = input_name_ptr.get();
        input_names.push_back(input_name_ptr.get());
        // std::cout << "Detected Input " << i << ": " << input_name << std::endl;
    }

Urgency

ASAP

Platform

Linux

OS Version

Ubuntu 22.04

ONNX Runtime Installation

Built from Source

ONNX Runtime Version or Commit ID

1.20

ONNX Runtime API

C++

Architecture

X86

Execution Provider

TensorRT

Execution Provider Library Version

TensorRT 10.0.0.6