find_make_group_parser for depthwise

[NickYangMin]

Describe the bug

def find_make_group_parser(self, node_name, name2module):
    """Find the corresponding make_group_parser according to the
    ``node_name``"""
    if 'concat' in node_name and node_name not in name2module:
        return MAKE_GROUP_PARSER_DICT['concat']
    elif 'chunk' in node_name and node_name not in name2module:
        return MAKE_GROUP_PARSER_DICT['chunk']
    elif (node_name in name2module
          and isinstance(name2module[node_name], nn.Conv2d)
          and name2module[node_name].in_channels
          == name2module[node_name].groups):
        return MAKE_GROUP_PARSER_DICT['depthwise']
    else:
        return MAKE_GROUP_PARSER_DICT['common']

if in_channels is 1，there may be a mistake

[HIT-cwh]

I'm sorry for the late reply and the inconvenience to you.
You are right, and in_channels, out_channels and groups should be all the same in depth-wise conv.
Are you interested in making a PR to fix this bug？

[NickYangMin]

I do not know How to do it, is there any manual？

[HIT-cwh]

Pr Submission Guidelines:
For English: https://mmcv.readthedocs.io/zh_CN/latest/community/pr.html and https://mmcv.readthedocs.io/zh_CN/latest/community/contributing.html
For Chinese: https://github.com/open-mmlab/mmcv/blob/master/CONTRIBUTING.md

PR welcome！