Yolov5 improvement 15: network lightweight method deep separable convolution

 ​ front said ： As the current advanced deep learning target detection algorithm YOLOv5, A large number of trick, But there is still room for improvement , For the detection difficulties in specific application scenarios , There are different ways to improve . 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 ： One of the problems of deep learning target detection model is that it is too large , Facing the problem of insufficient memory , Second, these scenarios require low latency , In other words, the response speed should be fast , Imagine the pedestrian detection system of self driving cars. What terrible things will happen if the speed is slow? . therefore , Research small and efficient CNN Models are crucial in these scenarios , At least for now , Although the hardware will be faster and faster in the future . This paper attempts to transform ordinary convolution into deep separable convolution , To realize the lightweight of the network model , Balance speed and accuracy .

Same series of articles ：YOLOv5 Improvement 13 ： Backbone network C3 Replace with lightweight network EfficientNetv2_ AI algorithm engineer 0301 The blog of -CSDN Blog https://blog.csdn.net/m0_70388905/article/details/125612096?spm=1001.2014.3001.5502YOLOv5 Improvement 12 ： Backbone network C3 Replace with lightweight network ShuffleNetV2_ AI algorithm engineer 0301 The blog of -CSDN Blog https://blog.csdn.net/m0_70388905/article/details/125612052https://blog.csdn.net/m0_70388905/article/details/125612052YOLOv5 Improvement Xi ： Backbone network C3 Replace with lightweight network MobileNetV3_ AI algorithm engineer 0301 The blog of -CSDN Blog https://blog.csdn.net/m0_70388905/article/details/125593267https://blog.csdn.net/m0_70388905/article/details/125593267

principle ：

Conventional convolution ： For one 5×5 Pixels 、 Three channels （shape by 5×5×3）, after 3×3 The convolution layer of the convolution kernel （ Suppose the number of output channels is 4, Then convolution kernel shape by 3×3×3×4, Final output 4 individual Feature Map, If there is same padding Then the size is the same as the input layer （5×5）, If not, the dimension becomes 3×3

Depth separates the convolution ：Depthwise Convolution A convolution kernel of is responsible for a channel , A channel is convoluted by only one convolution kernel . a sheet 5×5 Pixels 、 Three channel color input picture （shape by 5×5×3）,Depthwise Convolution First, after the first convolution operation ,DW Completely in a two-dimensional plane . The number of convolution kernels is the same as the number of channels in the upper layer （ The channel corresponds to the convolution kernel one by one ）. So a three channel image is generated after operation 3 individual Feature map( If there is same padding Then the size is the same as that of the input layer 5×5), As shown in the figure below .

Fang Law ：

Step 1 modify common.py, increase ghostC3 modular .

def DWConv(c1, c2, k=1, s=1, act=True):
    # Depthwise convolution
    return Conv(c1, c2, k, s, g=math.gcd(c1, c2), act=act)
class Conv(nn.Module):
    # Standard convolution
    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True):  # ch_in, ch_out, kernel, stride, padding, groups
        super(Conv, self).__init__()
        self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=False)
        self.bn = nn.BatchNorm2d(c2)
        self.act = nn.SiLU() if act is True else (act if isinstance(act, nn.Module) else nn.Identity())

    def forward(self, x):# Network execution sequence 
        return self.act(self.bn(self.conv(x)))

    def fuseforward(self, x):
        return self.act(self.conv(x))

The second step ： take yolo.py Registration module in .

if m in [Conv,MobileNetV3_InvertedResidual,ShuffleNetV2_InvertedResidual,ghostc3,DWconv

]:

The third step ： Make changes yaml file

junction fruit ： I have done a lot of experiments on multiple data sets , For different data sets, the effect is different ,map Value down , But the size of the weight model decreases , The parameter quantity decreases .

Let me know ： The next content will continue to share the sharing of network lightweight methods . Interested friends can pay attention to me , If you have questions, you can leave a message or chat with me in private

PS： The replacement of backbone network is not only applicable to improvement YOLOv5, You can also improve others YOLO Network and target detection network , such as YOLOv4、v3 etc. .

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

​