YOLOv5改进（SAConv，SAC）

最新推荐文章于 2024-10-04 12:03:59 发布

eagleflying_cau

最新推荐文章于 2024-10-04 12:03:59 发布

阅读量1.1k

点赞数

文章标签： YOLO python 数学建模

本文链接：https://blog.csdn.net/eagleflying_cau/article/details/131146615

版权

文章提出了一种改进的卷积神经网络层(ConvAWS2d和SAConv2d)，用于YOLOv5模型。这些新层增加了权重标准化和自适应上下文处理，提升了模型对特征的捕获能力。同时，介绍了Bottleneck_SAC和C3_SAC结构，优化了网络的深度和宽度。通过修改配置文件并集成到YOLOv5中，可以观察到模型性能的提高。

摘要由CSDN通过智能技术生成

1.论文地址

https://arxiv.org/pdf/2006.02334.pdf

2.方法

（1）将代码添加到models/commen.py中

class ConvAWS2d(nn.Conv2d):
    def __init__(self,
                 in_channels,
                 out_channels,
                 kernel_size,
                 stride=1,
                 padding=0,
                 dilation=1,
                 groups=1,
                 bias=True):
        super().__init__(
            in_channels,
            out_channels,
            kernel_size,
            stride=stride,
            padding=padding,
            dilation=dilation,
            groups=groups,
            bias=bias)
        self.register_buffer('weight_gamma', torch.ones(self.out_channels, 1, 1, 1))
        self.register_buffer('weight_beta', torch.zeros(self.out_channels, 1, 1, 1))

    def _get_weight(self, weight):
        weight_mean = weight.mean(dim=1, keepdim=True).mean(dim=2,
                                  keepdim=True).mean(dim=3, keepdim=True)
        weight = weight - weight_mean
        std = torch.sqrt(weight.view(weight.size(0), -1).var(dim=1) + 1e-5).view(-1, 1, 1, 1)
        weight = weight / std
        weight = self.weight_gamma * weight + self.weight_beta
        return weight

    def forward(self, x):
        weight = self

最低0.47元/天解锁文章