Yolov5 improvement 5: improve the feature fusion network panet to bifpn

  front       said ： As the current advanced deep learning target detection algorithm YOLOv5, A large number of trick, But when dealing with some complex background problems , It is still prone to the problem of mistakes and omissions . Subsequent articles , Focus on YOLOv5 How to improve is introduced in detail , The purpose is to provide their own meager help and reference for those who need innovation in scientific research or friends who need to achieve better results in engineering projects .

solve the problem ： Join in BIFPN Weighted two-way pyramid structure , Improve the detection effect of different scales

Add method ：

First step ：common.py structure Concat_BIFPN modular .

class Concat_BIFPN(nn.Module):
    # Concatenate a list of tensors along dimension
    def __init__(self, c1, c2):
        super(Concat_BIFPN, self).__init__()
        self.relu = nn.ReLU()
        self.w1 = nn.Parameter(torch.ones(2, dtype=torch.float32), requires_grad=True)
        self.w2 = nn.Parameter(torch.ones(3, dtype=torch.float32), requires_grad=True)
        self.epsilon = 0.0001
        self.conv = nn.Conv2d(c1, c2, kernel_size=1, stride=1, padding=0)
        self.swish = MemoryEfficientSwish()

    def forward(self, x):
        outs = self._forward(x)
        return outs

    def _forward(self, x):
        if len(x) == 2:
            # w = self.relu(self.w1)
            w = self.w1
            weight = w / (torch.sum(w, dim=0) + self.epsilon)
            # Connections for P6_0 and P7_0 to P6_1 respectively
            x = self.conv(self.swish(weight[0] * x[0] + weight[1] * x[1]))
        elif len(x) == 3:
            # w = self.relu(self.w2)
            w = self.w2
            weight = w / (torch.sum(w, dim=0) + self.epsilon)
            x = self.conv(self.swish(weight[0] * x[0] + weight[1] * x[1] + weight[2] * x[2]))

        return x

The second step ：yolo.py Register in Concat_BIFPNt modular

        elif m is Concat_BIFPN:
             c2 = max([ch[x] for x in f])#2021.11.11 Change fit bifpn Use 

The third step ： modify yaml file , Need modification head（ Feature fusion network ）.

 

Step four ： take train.py In this article yaml File can , Start training .

  junction     fruit ： I have done a lot of experiments on multiple data sets , For different data sets, the effect is different , There are also differences in the methods of adding locations to the same dataset , You need to experiment . Most cases are effective and improved .

Let me know ： The next content sharing adds a small target detection layer . Interested friends can pay attention to me , If you have questions, you can leave a message or chat with me in private

PS：, Not only can it be added YOLOv5, It can also be added to any other deep learning network , Whether it is classification, detection or segmentation , Mainly in the field of computer vision , May have different degrees of improvement effect .

Last , I hope I can powder each other , Be a friend , Learn and communicate together .