retinanet 部署_RetinaNet (二) - 网络架构

Focal Loss for Dense Object Detection

上篇文章简单介绍了Focal loss，该方法现已被广泛应用。除此之外，个人觉得原文中提到的RetinaNet值得关注，看了代码后着重对FPN和分类/回归子网络的细节进行整理。Figure 1

RetinaNet的网络架构如上图所示，可以简单看作是ResNet+FPN+分类/回归子网络。关于ResNet，网上的资料很多，不再赘述。

一、FPN

有关FPN，可以参考我的文章进行理解：冲鸭嘎嘎：CVPR 2017 - FPN理解 - 简单高效的特征金字塔​zhuanlan.zhihu.com

FPN对应的代码块如下:

class PyramidFeatures(nn.Module):

def __init__(self, C3_size, C4_size, C5_size, feature_size=256):

super(PyramidFeatures, self).__init__()

# upsample C5 to get P5 from the FPN paper

self.P5_1 = nn.Conv2d(C5_size, feature_size, kernel_size=1, stride=1, padding=0)

self.P5_upsampled = nn.Upsample(scale_factor=2, mode='nearest')

self.P5_2 = nn.Conv2d(feature_size, feature_size, kernel_size=3, stride=1, padding=1)

# add P5 elementwise to C4

self.P4_1 = nn.Conv2d(C4_size, feature_size, kernel_size=1, stride=1, padding=0)

self.P4_upsampled = nn.Upsample(scale_factor=2, mode='nearest')

self.P4_2 = nn.Conv2d(feature_size, feature_size, kernel_size=3, stride=1, padding=1)

# ad