Fix a bug that training is stuck while detection model is trained on distrubited environment

[eunwoosh]

Summary

This PR fixes #3635

How this change solves the bug

In distributed training, torchmetric package tries to sync values across processes.
If one process has a value in bbox, label or scores and other process not, then torchmetric makes empty torch Tensor.
But if dtype of tensor between processes is different, then process is stuck during sync.
To avoid it, this PR specifies dtype properly.

How to test

Checklist

• I have added unit tests to cover my changes.​
• I have added integration tests to cover my changes.​
• I have ran e2e tests and there is no issues.
• I have added the description of my changes into CHANGELOG in my target branch (e.g., CHANGELOG in develop).​
• I have updated the documentation in my target branch accordingly (e.g., documentation in develop).
• I have linked related issues.

License

• I submit my code changes under the same Apache License that covers the project.
  Feel free to contact the maintainers if that's a concern.
• I have updated the license header for each file (see an example below).

# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 81.20%. Comparing base (0a395b2) to head (09bc0b1).
Report is 1 commits behind head on develop.

Additional details and impacted files

@@             Coverage Diff             @@
##           develop    #3904      +/-   ##
===========================================
- Coverage    81.21%   81.20%   -0.02%     
===========================================
  Files          283      283              
  Lines        27169    27169              
===========================================
- Hits         22065    22062       -3     
- Misses        5104     5107       +3     

Flag	Coverage Δ
py310	?
py311	81.20% <ø> (+<0.01%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.