Mvit code error[Bug]

[commandermsv]

Branch

main branch (1.x version, such as v1.0.0, or dev-1.x branch)

Prerequisite

• I have searched Issues and Discussions but cannot get the expected help.
• I have read the documentation but cannot get the expected help.
• The bug has not been fixed in the latest version.

Environment

While training mvit-base-p244_32x3x1_kinetics400-rgb.py, I'm continuously getting this below msg,

/mmaction2/mmaction/models/utils/blending_utils.py:151: UserWarning: floordiv is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').

Describe the bug

While training mvit-base-p244_32x3x1_kinetics400-rgb.py, I'm continuously getting this below msg,

/mmaction2/mmaction/models/utils/blending_utils.py:151: UserWarning: floordiv is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').

How to solve this?

Reproduces the problem - code sample

No response

Reproduces the problem - command or script

No response

Reproduces the problem - error message

No response

Additional information

No response

[Dai-Wenxun]

This warning message is indicating that the usage of floordiv function in the code is deprecated in PyTorch, and that it will have a different behavior in a future version of PyTorch. Currently, floordiv function rounds towards zero, which can cause incorrect rounding for negative values.

Use torch.div(a, b, rounding_mode='trunc') instead of floordiv, which will provide the same behavior as floordiv in the current version of PyTorch.

We fix this warning in #2449.