Logic Error in experimental Unity Plugin HelloTFLite.cs Sample Code

[Tom-James-Marsden]

Issue type

Documentation Bug

Have you reproduced the bug with TensorFlow Nightly?

No

Source

binary

TensorFlow version

tf 2.15

Custom code

No

OS platform and distribution

Windows 11

Mobile device

No response

Python version

No response

Bazel version

No response

GCC/compiler version

No response

CUDA/cuDNN version

No response

GPU model and memory

No response

Current behavior?

Currently in HelloTFLite.cs in the experimental Unity Plugin example project there is a logic error at line 59
Here is the function i am looking at

  void Start () {
    Debug.LogFormat("TensorFlow Lite Verion: {0}", Interpreter.GetVersion());

    var options = new Interpreter.Options() {
      threads = 2,
    };
    interpreter = new Interpreter(model.bytes, options);

    int inputCount = interpreter.GetInputTensorCount();
    int outputCount = interpreter.GetOutputTensorCount();
    for (int i = 0; i < inputCount; i++) {
      Debug.LogFormat("Input {0}: {1}", i, interpreter.GetInputTensorInfo(i));
    }
    for (int i = 0; i < inputCount; i++) {
      Debug.LogFormat("Output {0}: {1}", i, interpreter.GetOutputTensorInfo(i));
    }
  }

In the second for loop the bound inputCount should be outputCount as it is looping through the output tensors

Standalone code to reproduce the issue

Load in a model with input and output tensors of different length and you will find that either not all the tensors get logged or there is an error.

Relevant log output

No response

[LakshmiKalaKadali]

Hi @Tom-James-Marsden,

I have gone through the file and raised a PR. Please track the PR #63131.

Thank You

[Tom-James-Marsden]

Even though this is such a tiny bug in some experimental code from a project that isn't going to be gone further with I'm dead excited I got to point out and help fix a part of this repository. Whoop whoop

[google-ml-butler]

Are you satisfied with the resolution of your issue?
Yes
No