Add PyTorch 1.12 and 1.13 to GH Actions

[codecov[bot]]

Codecov Report

Base: 92.10% // Head: 92.11% // Increases project coverage by +0.01% :tada:

Coverage data is based on head (2b00733) compared to base (b7cb695). Patch coverage: 100.00% of modified lines in pull request are covered.

Additional details and impacted files

```diff @@ Coverage Diff @@ ## main #478 +/- ## ========================================== + Coverage 92.10% 92.11% +0.01% ========================================== Files 11 11 Lines 785 786 +1 ========================================== + Hits 723 724 +1 Misses 62 62 ``` | Flag | Coverage Δ | | |---|---|---| | unittests | `92.11% <100.00%> (+0.01%)` | :arrow_up: | Flags with carried forward coverage won't be shown. [Click here](https://docs.codecov.io/docs/carryforward-flags?utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Zhiqiang+Wang#carryforward-flags-in-the-pull-request-comment) to find out more. | [Impacted Files](https://codecov.io/gh/zhiqwang/yolov5-rt-stack/pull/478?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Zhiqiang+Wang) | Coverage Δ | | |---|---|---| | [test/test\_runtime\_ort.py](https://codecov.io/gh/zhiqwang/yolov5-rt-stack/pull/478?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Zhiqiang+Wang#diff-dGVzdC90ZXN0X3J1bnRpbWVfb3J0LnB5) | `98.63% <100.00%> (+0.01%)` | :arrow_up: | Help us with your feedback. Take ten seconds to tell us [how you rate us](https://about.codecov.io/nps?utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Zhiqiang+Wang). Have a feature suggestion? [Share it here.](https://app.codecov.io/gh/feedback/?utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Zhiqiang+Wang)

:umbrella: View full report at Codecov.
:loudspeaker: Do you have feedback about the report comment? Let us know in this issue.

[CLAassistant]

Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you all sign our Contributor License Agreement before we can accept your contribution.
1 out of 2 committers have signed the CLA.

:white_check_mark: zhiqwang
:x: dependabot[bot]
_{You have signed the CLA already but the status is still pending? Let us recheck it.}

[ialdencoots]

The unittest failures seem to be related to casting incompatibilities in the newer pytorch versions. If you change this following line

https://github.com/zhiqwang/yolov5-rt-stack/blob/16af0f1145c12bfb8a08ca60aa5fafe3ba4bee45/yolort/models/box_head.py#L241

to

gain = torch.ones(7, device=device).long()

the tests with the RuntimeError: result type Float can't be cast to the desired output type long int error should pass.

[zhiqwang]

Thanks @ialdencoots for your help here, it works!