4.算法一直系列第四篇模型转换best.pt转onnx,运行export.py修改文件

 1.修改为自己数据集的data.yaml

2.修改为自己训练得到的best.py权重文件

    parser = argparse.ArgumentParser()
    parser.add_argument("--data", type=str, default=ROOT / "dataset/car/data.yaml", help="dataset.yaml path")
    parser.add_argument("--weights", nargs="+", type=str, default=ROOT / "best.pt", help="model.pt path(s)")

3修改iopset’的defaut修改为12（一定要修改为12） 

    parser.add_argument("--opset", type=int, default=12, help="ONNX: opset version")

4.i 修改models/yolo.py文件
修改其Detect类下的forward函数。

def forward(self, x):
    """Processes input through YOLOv5 layers, altering shape for detection: `x(bs, 3, ny, nx, 85)`."""
    z = []  # inference output
    for i in range(self.nl):
        x[i] = self.m[i](x[i])  # conv
        bs, _, ny, nx = x[i].shape  # x(bs,255,20,20) to x(bs,3,20,20,85)
        x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()

        if not self.training:  # inference
            if self.dynamic or self.grid[i].shape[2:4] != x[i].shape[2:4]:
                self.grid[i], self.anchor_grid[i] = self._make_grid(nx, ny, i)

            if isinstance(self, Segment):  # (boxes + masks)
                xy, wh, conf, mask = x[i].split((2, 2, self.nc + 1, self.no - self.nc - 5), 4)
                xy = (xy.sigmoid() * 2 + self.grid[i]) * self.stride[i]  # xy
                wh = (wh.sigmoid() * 2) ** 2 * self.anchor_grid[i]  # wh
                y = torch.cat((xy, wh, conf.sigmoid(), mask), 4)
            else:  # Detect (boxes only)
                xy, wh, conf = x[i].sigmoid().split((2, 2, self.nc + 1), 4)
                xy = (xy * 2 + self.grid[i]) * self.stride[i]  # xy
                wh = (wh * 2) ** 2 * self.anchor_grid[i]  # wh
                y = torch.cat((xy, wh, conf), 4)
            z.append(y.view(bs, self.na * nx * ny, self.no))


    return x if self.training else (torch.cat(z, 1),) if self.export else (torch.cat(z, 1), x)

模型转换时将上述部分改为

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

结果运行export.py发生报错 修改export.py这部分代码

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

将上述代码将进行修改 

shape = tuple(y[0].shape)

5.运行export.py