maskrcnn-benchmar 代码详解之 fpn.py

前言

FPN网络主要应用于多层特征提取，使用多尺度的特征层来进行目标检测，可以利用不同的特征层对于不同大小特征的敏感度不同，将他们充分利用起来，以更有利于目标检测，在maskrcnn benchmark中代码详解如下：

# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
import torch
import torch.nn.functional as F
from torch import nn


class FPN(nn.Module):
    """
    Module that adds FPN on top of a list of feature maps.
    The feature maps are currently supposed to be in increasing depth
    order, and must be consecutive
    """

    def __init__(
        self, in_channels_list, out_channels, conv_block, top_blocks=None
    ):
        """
        Arguments:
            in_channels_list (list[int]): number of channels for each feature map that
                will be fed 每一个特征图上输入数据的通道数
            out_channels (int): number of channels of the FPN representation　FPN结构输出特征的通道数
            top_blocks (nn.Module or None): if p