Yolov5 输出 onnx 模型配置

修改./models/yolo.py

找到forward函数定义，替换全部函数为

def forward(self, x):
    z = []  # inference output
    for i in range(self.nl):
        x[i] = self.m[i](x[i])  # conv

    return x

修改./export.py

shape = tuple((y[0] if isinstance(y, tuple) else y).shape)  # model output shape

改为

shape = tuple((y[0] if isinstance(y, tuple) else y))  # model output shape

输出onnx模型指令

python export.py --weights yolov5s.pt --img 640 --batch 1 --include onnx