setting varied learning rate for different layers

[d-li14]

@xiaomengyc
Hi, thanks for releasing the wonderful implementation of your work!
I noticed from this snippet since https://github.com/xiaomengyc/SPG/blob/master/exper/my_optim.py#L12, you try to multiply the lr for the last conv layer before GAP in the main branch by 10. But the model's parameters don't include one with 'cls' in its name, maybe 'classifier_1' should be considered?