yolov5导出onnx模型后，验证模型报错

参考源码：
https://github.com/ultralytics/yolov5/tree/v5.0
先看看具体报错

原因就出在这里，在5.0版本中这里默认选择inplace操作，导致这个问题

class Detect(nn.Module):
    stride = None  # strides computed during build
    export = False  # onnx export

    def __init__(self, nc=80, anchors=(), ch=()):  # detection layer
        super(Detect, self).__init__()
        self.nc = nc  # number of classes
        self.no = nc + 5  # number of outputs per anchor
        self.nl = len(anchors)  # number of detection layers
        self.na = len(anchors[0]) // 2  # number of anchors
        self.grid = [torch.zeros(1)] * self.nl  # init grid
        a = torch.tensor(anchors).float().view(self.nl, -1, 2)
        self.register_buffer('anchors', a)  # shape(nl,na,2)
        self.register_buffer('anchor_grid', a.clone().view(self.nl, 1, -1, 1, 1, 2))  # shape(nl,1,na,1,1,2)
        self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch)  # output conv

    def forward(self, x):
        # x = x.copy()  # for profiling
        z = []  # inference output
        self.training |= self.export
        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.grid[i].shape[2:4] != x[i].shape[2:4]:
                    self.grid[i] = self._make_grid(nx, ny).to(x[i].device)

                y = x[i].sigmoid()
                y[..., 0:2] = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i]  # xy
                y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]  # wh
                z.append(y.view(bs, -1, self.no))

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

将其修改成这样，不在原数组上直接操作，就不会报错了，v5.0前的版本好像有inplace这个参数可以控制。

class Detect(nn.Module):
    stride = None  # strides computed during build
    # export = False  # onnx export

    def __init__(self, nc=80, anchors=(), ch=()):  # detection layer
        super(Detect, self).__init__()
        self.nc = nc  # number of classes
        self.no = nc + 5  # number of outputs per anchor
        self.nl = len(anchors)  # number of detection layers
        self.na = len(anchors[0]) // 2  # number of anchors
        self.grid = [torch.zeros(1)] * self.nl  # init grid
        a = torch.tensor(anchors).float().view(self.nl, -1, 2)
        self.register_buffer('anchors', a)  # shape(nl,na,2)
        self.register_buffer('anchor_grid', a.clone().view(self.nl, 1, -1, 1, 1, 2))  # shape(nl,1,na,1,1,2)
        self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch)  # output conv

    def forward(self, x):
        # x = x.copy()  # for profiling
        z = []  # inference output
        # self.training |= self.export
        for i in range(self.nl):
            x[i] = self.m[i](x[i])  # conv
            #修改1
            bs, _, ny, nx = map(int, x[i].shape)  # x(bs,255,20,20) to x(bs,3,20,20,85)
             #修改2
            x[i] = x[i].view(-1, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()


            if not self.training:  # inference
                self.grid[i] = self._make_grid(nx, ny).to(x[i].device)

                y = x[i].sigmoid()
				#修改3
                xy = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i]  # xy
                wh = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i].view(1, self.na, 1, 1, 2)  # wh
                y = torch.cat((xy, wh, y[..., 4:]), -1)
				#修改4
                z.append(y.view(-1, int(y.size(1) * y.size(2) * y.size(3)), self.no))

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

还可以参考b站上一个大神讲的怎么正确的导出onnx模型，看完后，跟着操作，你会发现你导出的模型看起来确实好看多了
https://www.bilibili.com/video/BV1Xw411f7FW/?spm_id_from=333.337