yolov5 7.0结构图

很高兴为您解答。YOLOv5 7.0的结构图如下所示：[^1]

Model Summary: 308 layers, 2.54287e+07 parameters, 0 gradients
================================================================
Total params: 34,864,019
Trainable params: 34,864,019
Non-trainable params: 0
--
Input size (MB): 3.00
Forward/backward pass size (MB): 1835.29
Params size (MB): 132.73
Estimated Total Size (MB): 1971.03
--

其中，模型总共包含308层，参数量约为2.54287e+07。整体结构如下：
1. Backbone: CSPDarknet53
2. Neck: SPP (Spatial Pyramid Pooling)
3. Head: YOLOv5 Head