盘点目标检测中的特征融合技巧(根据YOLO v4总结)
极市平台
共 13121字,需浏览 27分钟
·
2020-07-28 15:25
加入极市专业CV交流群,与 10000+来自港科大、北大、清华、中科院、CMU、腾讯、百度 等名校名企视觉开发者互动交流!
同时提供每月大咖直播分享、真实项目需求对接、干货资讯汇总,行业技术交流。关注 极市平台 公众号 ,回复 加群,立刻申请入群~
特征融合分类
Feature Pyramid Network(FPN)
import torch.nn as nn
import torch.nn.functional as F
import math
class Bottleneck(nn.Module):
expansion = 4
def __init__(self, in_planes, planes, stride=1, downsample=None):
super(Bottleneck, self).__init__()
self.bottleneck = nn.Sequential(
nn.Conv2d(in_planes, planes, 1, bias=False),
nn.BatchNorm2d(planes),
nn.ReLU(inplace=True),
nn.Conv2d(planes, planes, 3, stride, 1, bias=False),
nn.BatchNorm2d(planes),
nn.ReLU(inplace=True),
nn.Conv2d(planes, self.expansion * planes, 1, bias=False),
nn.BatchNorm2d(self.expansion * planes),
)
self.relu = nn.ReLU(inplace=True)
self.downsample = downsample
def forward(self, x):
identity = x
out = self.bottleneck(x)
if self.downsample is not None:
identity = self.downsample(x)
out += identity
out = self.relu(out)
return out
class FPN(nn.Module):
def __init__(self, layers):
super(FPN, self).__init__()
self.inplanes = 64
self.conv1 = nn.Conv2d(3, 64, 7, 2, 3, bias=False)
self.bn1 = nn.BatchNorm2d(64)
self.relu = nn.ReLU(inplace=True)
self.maxpool = nn.MaxPool2d(3, 2, 1)
self.layer1 = self._make_layer(64, layers[0])
self.layer2 = self._make_layer(128, layers[1], 2)
self.layer3 = self._make_layer(256, layers[2], 2)
self.layer4 = self._make_layer(512, layers[3], 2)
self.toplayer = nn.Conv2d(2048, 256, 1, 1, 0)
self.smooth1 = nn.Conv2d(256, 256, 3, 1, 1)
self.smooth2 = nn.Conv2d(256, 256, 3, 1, 1)
self.smooth3 = nn.Conv2d(256, 256, 3, 1, 1)
self.latlayer1 = nn.Conv2d(1024, 256, 1, 1, 0)
self.latlayer2 = nn.Conv2d( 512, 256, 1, 1, 0)
self.latlayer3 = nn.Conv2d( 256, 256, 1, 1, 0)
def _make_layer(self, planes, blocks, stride=1):
downsample = None
if stride != 1 or self.inplanes != Bottleneck.expansion * planes:
downsample = nn.Sequential(
nn.Conv2d(self.inplanes, Bottleneck.expansion * planes, 1, stride, bias=False),
nn.BatchNorm2d(Bottleneck.expansion * planes)
)
layers = []
layers.append(Bottleneck(self.inplanes, planes, stride, downsample))
self.inplanes = planes * Bottleneck.expansion
for i in range(1, blocks):
layers.append(Bottleneck(self.inplanes, planes))
return nn.Sequential(*layers)
def _upsample_add(self, x, y):
_,_,H,W = y.shape
return F.upsample(x, size=(H,W), mode='bilinear') + y
def forward(self, x):
c1 = self.maxpool(self.relu(self.bn1(self.conv1(x))))
c2 = self.layer1(c1)
c3 = self.layer2(c2)
c4 = self.layer3(c3)
c5 = self.layer4(c4)
p5 = self.toplayer(c5)
p4 = self._upsample_add(p5, self.latlayer1(c4))
p3 = self._upsample_add(p4, self.latlayer2(c3))
p2 = self._upsample_add(p3, self.latlayer3(c2))
p4 = self.smooth1(p4)
p3 = self.smooth2(p3)
p2 = self.smooth3(p2)
return p2, p3, p4, p5
PANet(Path Aggregation Network)
MLFPN
ASFF:自适应特征融合方式
Bi-FPN
评论