FLOPS computation device bug fix

[JunnYu]

fix Lyken17/pytorch-OpCounter#113 , inputs device should be same with model parameters' device

🛠️ PR Summary

_{Made with ❤️ by Ultralytics Actions}

🌟 Summary

Improved FLOPS calculation compatibility across different compute devices.

📊 Key Changes

• Modified the FLOPS calculation to create the input tensor on the same device as the model's parameters.
• Ensured the input size is correctly handled when provided as an integer rather than a list.

🎯 Purpose & Impact

• 🏃‍♂️ Ensures consistent FLOPS calculation regardless of whether the model is on a CPU, GPU, or any other compute device, thus enhancing cross-platform compatibility.
• 👌 The update prevents potential errors or discrepancies that may have arisen from assuming the input tensor's device, making performance profiling more reliable.
• 💡 Users now have more accurate insights into the computational complexity of their models with different input sizes, leading to better optimization and hardware utilization.

[JunnYu]

[github-actions]

Hello @JunnYu, thank you for submitting a PR! To allow your work to be integrated as seamlessly as possible, we advise you to:

• Verify your PR is up-to-date with origin/master. If your PR is behind origin/master update by running the following, replacing 'feature' with the name of your local branch:

git remote add upstream https://github.com/ultralytics/yolov5.git
git fetch upstream
git checkout feature  # <----- replace 'feature' with local branch name
git rebase upstream/master
git push -u origin -f

• Verify all Continuous Integration (CI) checks are passing.
• Reduce changes to the absolute minimum required for your bug fix or feature addition. "It is not daily increase but daily decrease, hack away the unessential. The closer to the source, the less wastage there is." -Bruce Lee

[glenn-jocher]

@JunnYu this PR is merged. Thank you for your contributions!