feat(CenterPoint): Add finetuning to CenterPoint by freezing certain layers

[KSeangTan]

Summary

Add a feature to freeze parameters of each layer in CenterPoint.
For example, users can specify:

pts_backbone=dict(
        type="SECOND",
        in_channels=32,
        out_channels=[64, 128, 256],
        layer_nums=[3, 5, 5],
        layer_strides=[1, 2, 2],
        norm_cfg=dict(type="BN", eps=1e-3, momentum=0.01),
        conv_cfg=dict(type="Conv2d", bias=False),
        frozen_stages=[0, 1, 2]
    ),

to freeze all layers in the backbone during finetuning

[scepter914]

LGTM 👍

Let's try various experiments of fine tuning, and if any issues arise, we can fix or revert them as needed.