贴一张Yolov3网络结构图~
filter = 3*(80+1+4) = 255
Yolov3 is a fully convolutional network. It has 75 convolutional layers, with skip connections and upsampling layers. No form of pooling is used, and a convolutional layer with stride 2 is used to downsample the feature maps, which helps in preventing loss of low-level features often attributed to pooling.
详细内容见:A Closer Look at YOLOv3