Mobilenet V3 to ONNX support

[Macok]

Motivation

Support conversion of mmpretrain's Mobilenet V3 classification models to ONNX.

Modification

Fixes error that was arising during conversion to ONNX: #2245

[CLAassistant]

All committers have signed the CLA.

[RunningLeon]

@Macok hi, thanks for your PR. Could you add mobilenetv3 in the regression test config and run the test to see whether some backends are supported.

1. pull docker image openmmlab/mmdeploy:ubuntu20.04-cuda11.3-mmdeploy1.2.0 and create container by refering to https://mmdeploy.readthedocs.io/en/latest/01-how-to-build/build_from_docker.html
2. Add config for mobilenetv3 in https://github.com/open-mmlab/mmdeploy/blob/main/tests/regression/mmpretrain.yml#L241
3. run python3 tools/regressiont_test.py --codebase mmpretrain --models MobileNetV3 --work-dir ./workdir
4. check regression result in ./workdir and update model support list in https://github.com/open-mmlab/mmdeploy/blob/main/docs/zh_cn/04-supported-codebases/mmpretrain.md and https://github.com/open-mmlab/mmdeploy/blob/main/docs/en/04-supported-codebases/mmpretrain.md

[OpenMMLab-Assistant-004]

Hi @Macok,

We'd like to express our appreciation for your valuable contributions to the mmdeploy. Your efforts have significantly aided in enhancing the project's quality.
It is our pleasure to invite you to join our community thorugh Discord_Special Interest Group (SIG) channel. This is a great place to share your experiences, discuss ideas, and connect with other like-minded people. To become a part of the SIG channel, send a message to the moderator, OpenMMLab, briefly introduce yourself and mention your open-source contributions in the #introductions channel. Our team will gladly facilitate your entry. We eagerly await your presence. Please follow this link to join us: ​https://discord.gg/UjgXkPWNqA.

If you're on WeChat, we'd also love for you to join our community there. Just add our assistant using the WeChat ID: openmmlabwx. When sending the friend request, remember to include the remark "mmsig + Github ID".

Thanks again for your awesome contribution, and we're excited to have you as part of our community!

[codecov]

Codecov Report

Patch has no changes to coverable lines.

Files Changed	Coverage
...eploy/codebase/mmpretrain/deploy/classification.py	0.00%

📢 Thoughts on this report? Let us know!.

[RunningLeon]

LGTM

[AllentDan]

Why not update its performance on the ONNXRuntime backend?