FairMOT代码解析之self.base = globals()[base_name](pretrained=pretrained)

对于代码解读： 

\FairMOT-master\src\lib\models\networks\pose_dla_dcn.py
line433
self.base = globals()[base_name](pretrained=pretrained)

base_name的值是什么？不断追溯：

line426
class DLASeg(nn.Module):
    def __init__(self, base_name, heads, pretrained, down_ratio, final_kernel,
                 last_level, head_conv, out_channel=0):
        super(DLASeg, self).__init__()
        assert down_ratio in [2, 4, 8, 16]
        self.first_level = int(np.log2(down_ratio))
        self.last_level = last_level
        self.base = globals()[base_name](pretrained=pretrained)
        channels = self.base.channels

line484
def get_pose_net(num_layers, heads, head_conv=256, down_ratio=4):
  model = DLASeg('dla{}'.format(num_layers), heads,
                 pretrained=True,
                 down_ratio=down_ratio,
                 final_kernel=1,
                 last_level=5,