@@ -34,9 +34,9 @@ YOLOv3 networks are composed of base feature extraction network, multi-scale fea
...
@@ -34,9 +34,9 @@ YOLOv3 networks are composed of base feature extraction network, multi-scale fea
1. Feature extraction network: YOLOv3 ues [DarkNet53](https://arxiv.org/abs/1612.08242) for feature extracion,Darknet53 uses a full convolution structure, replacing the pooling layer with a convolution operation of step size 2, and adding Residual-block to avoid gradient dispersion when the number of network layers is too deep.
1. Feature extraction network: YOLOv3 ues [DarkNet53](https://arxiv.org/abs/1612.08242) for feature extracion,Darknet53 uses a full convolution structure, replacing the pooling layer with a convolution operation of step size 2, and adding Residual-block to avoid gradient dispersion when the number of network layers is too deep.
2. Feature fusion layer. In order to solve the problem that the previous YOLO version is not sensitive to small objects, YOLOv3 uses three different scale feature maps for target detection, which are 13*13, 26*26, 52*52, respectively, for detecting large, medium and small objects. The feature fusion layer selects the three scale feature maps produced by DarkNet as input, and draws on the idea of FPN (feature pyramid networks) to fuse the feature maps of each scale through a series of convolutional layers and upsampling.
2. Feature fusion layer. In order to solve the problem that the previous YOLO version is not sensitive to small objects, YOLOv3 uses three different scale feature maps for target detection, which are 13\*13, 26\*26, 52\*52, respectively, for detecting large, medium and small objects. The feature fusion layer selects the three scale feature maps produced by DarkNet as input, and draws on the idea of FPN (feature pyramid networks) to fuse the feature maps of each scale through a series of convolutional layers and upsampling.
3. Output layer: The output layer also uses a full convolution structure. The number of convolution kernels in the last convolutional layer is 255:3*(80+4+1)=255, and 3 indicates that a grid cell contains 3 bounding boxes. 4 represents the four coordinate information of the box, 1 represents the Confidence Score, and 80 represents the probability of 80 categories in the COCO dataset.
3. Output layer: The output layer also uses a full convolution structure. The number of convolution kernels in the last convolutional layer is 255:3\*(80+4+1)=255, and 3 indicates that a grid cell contains 3 bounding boxes. 4 represents the four coordinate information of the box, 1 represents the Confidence Score, and 80 represents the probability of 80 categories in the COCO dataset.
