1.综述

anchor即目标检测的先验框，retinanet的anchor有scales和ratios，根据每个pyramid_levels生成三个scales，三个ratios，然后形成九种先验框。
scales：anchor的大小（宽）
ratios：anchor的宽高比

2.参数：pyramid_levels, strides, sizes, ratios, scales

class Anchors(nn.Module):
    def __init__(self, pyramid_levels=None, strides=None, sizes=None, ratios=None, scales=None):
        super(Anchors, self).__init__()
        if pyramid_levels is None:
            self.pyramid_levels = [3, 4, 5, 6, 7]
        if strides is None:
            self.strides = [2 ** x for x in self.pyramid_levels]
        if sizes is None:
            self.sizes = [2 ** (x + 2) for x in self.pyramid_levels]
        if ratios is None:
            self.ratios = np.array([0.5, 1, 2])
        if scales is None:
            self.scales = np.array([2 ** 0, 2 ** (1.0 / 3.0), 2 ** (2.0 / 3.0)])

pyramid_level:feature map标号，对应resnet的p3层到p7层
strides：滑窗的步长
size：窗口的宽
ratios：宽高比
scales：面积比例