fix: add warmup to squeezenet_1.0 config to make the training be stable.

[PingqiLi]

Thank you for your contribution to the MindCV repo. Before submitting this PR, please make sure:

• [x] You have read the Contributing Guidelines on pull requests
• [x] Your code builds clean without any errors or warnings
• [x] You are using approved terminology
• [ ] You have added unit tests

Motivation

Squeezenet_1.0在以前的配置下不能稳定训练，偶尔会有validation accuracy 1.0的情况。为了使训练稳定，在训练配置的.yaml文件中增加了warmup_epochs=5。 SqueezeNet_1.0 could not be trained stably under the previous configuration, occasionally resulting in a validation accuracy of 1.0%. To stabilize the training, warmup_epochs=5 was added in the training configuration .yaml file.

Test Plan

(How should this PR be tested? Do you require special setup to run the test or repro the fixed bug?)

Related Issues and PRs

(Is this PR part of a group of changes? Link the other relevant PRs and Issues here. Use https://help.github.com/en/articles/closing-issues-using-keywords for help on GitHub syntax)

[The-truthh]

Please change the checkpoint path in squeezenet.py