网站建设用哪个,网站服务器安全防护,受欢迎的合肥网站建设,深圳建设工程交易网官网文章目录 文章地址网络各层结构代码实现 文章地址 An End-to-End Traffic Visibility Regression Algorithm文章通过训练搜集得到的真实道路图像数据集#xff08;Actual Road dense image Dataset, ARD#xff09;#xff0c;通过专业的能见度计和多人标注#xff0c;获得… 文章目录 文章地址网络各层结构代码实现 文章地址 An End-to-End Traffic Visibility Regression Algorithm文章通过训练搜集得到的真实道路图像数据集Actual Road dense image Dataset, ARD通过专业的能见度计和多人标注获得可靠的能见度标签数据集。构建网络进行训练获得了较好的能见度识别网络。网络包括特征提取​、多尺度映射​、特征融合​、非线性输出回归范围为[0,1]需要经过(0,0),(1,1)改用修改的sigmoid函数相较于ReLU更好。结构如下​ 网络各层结构 我认为红框位置与之相应的参数不匹配在Feature Extraction部分Reshape之后得到的特征图大小为4124124。紧接着接了一个卷积层Conv显示输入是3128128第二处红框MaxPool的kernel设置为88,特征图没有进行padding到全连接层的输入变为64117*117参数不对应 代码实现 Based on the ideas of the below paper, using PyTorch to build TVRNet.Reference: Qin H, Qin H. An end-to-end traffic visibility regression algorithm[J]. IEEE Access, 2021, 10: 25448-25454.​weishuo import torch from torch import nn import mathclass Inception(nn.Module):def __init__(self, in_planes, out_planes):super(Inception, self).__init__()self.conv1 nn.Conv2d(in_planes, out_planes, kernel_size1, padding0)self.conv3 nn.Conv2d(in_planes, out_planes, kernel_size3, padding1)self.conv5 nn.Conv2d(in_planes, out_planes, kernel_size5, padding2)self.conv7 nn.Conv2d(in_planes, out_planes, kernel_size7, padding3)def forward(self, x):out_1 self.conv1(x)out_3 self.conv3(x)out_5 self.conv5(x)out_7 self.conv7(x)out torch.cat((out_1, out_3, out_5, out_7), dim1)return outdef modify_sigmoid(x):return 1 / (1 torch.exp(-10*(x-0.5)))class TVRNet(nn.Module):def __init__(self, in_planes, out_planes):super(TVRNet, self).__init__()# (B, 3, 224, 224) —— (B, 3, 220, 220)self.FeatureExtraction_onestep nn.Sequential(nn.Conv2d(in_planes, 20, kernel_size5, padding0),nn.ReLU(inplaceTrue),)self.FeatureExtraction_maxpool nn.MaxPool2d((5, 1))self.MultiScaleMapping nn.Sequential(Inception(4, 16),nn.ReLU(inplaceTrue),nn.MaxPool2d(kernel_size8))self.FeatureIntegration nn.Sequential(nn.Linear(46656, 100),nn.ReLU(inplaceTrue),nn.Dropout(0.4),nn.Linear(100, out_planes))self.NonLinearRegression modify_sigmoiddef forward(self, x):x self.FeatureExtraction_onestep(x)x x.view((x.shape[0], 1, x.shape[1], -1))x self.FeatureExtraction_maxpool(x)x x.view(x.shape[0], x.shape[2], int(math.sqrt(x.shape[3])), int(math.sqrt(x.shape[3])))# print(x.shape)x self.MultiScaleMapping(x)# print(x.shape)x x.view(x.shape[0], -1)x self.FeatureIntegration(x)out self.NonLinearRegression(x)return outif __name__ __main__:a torch.randn(1,3,224,224)net TVRNet(3,3)b net(a)print(b.shape)