yolo pt转onnx导出

 1.代码修改

2.模型结构修改 

应修改为

self.training = True

3.要执行 export.py 文件

方法一：PyCharm软件中右键执行代码

方法二：cmd的终端中使用命令 python export.py 

报错处理：

解决办法

少了一个点

self.training = True

以下不变

 以下代码注释

以下模块升级

以下问题估计版本问题导致  torch 版本也确实不对 

self.training = True  少打了一个点

解决办法

更换环境

成功运行  但是模型有问题，更换了torch版本解决

 

最终解决办法

torch版本问题

代码修改

def parse_opt():
    parser = argparse.ArgumentParser()
    parser.add_argument('--data', type=str, default=ROOT / 'data/coco128.yaml', help='dataset.yaml path')
    parser.add_argument('--weights', type=str, default=ROOT / 'YOLO_Mask/score/train/exp_yolov5m/weights/best.pt', help='weights path')
    parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[640, 640], help='image (h, w)')
    parser.add_argument('--batch-size', type=int, default=1, help='batch size')
    parser.add_argument('--device', default='cpu', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
    parser.add_argument('--half', action='store_true', help='FP16 half-precision export')
    parser.add_argument('--inplace', action='store_true', help='set YOLOv5 Detect() inplace=True')
    parser.add_argument('--train', action='store_true', help='model.train() mode')
    parser.add_argument('--optimize', action='store_true', help='TorchScript: optimize for mobile')
    parser.add_argument('--int8', action='store_true', help='CoreML/TF INT8 quantization')
    parser.add_argument('--dynamic', action='store_true', help='ONNX/TF: dynamic axes')
    parser.add_argument('--simplify', action='store_true',default=True, help='ONNX: simplify model')
    parser.add_argument('--opset', type=int, default=13, help='ONNX: opset version')
    parser.add_argument('--topk-per-class', type=int, default=100, help='TF.js NMS: topk per class to keep')
    parser.add_argument('--topk-all', type=int, default=100, help='TF.js NMS: topk for all classes to keep')
    parser.add_argument('--iou-thres', type=float, default=0.45, help='TF.js NMS: IoU threshold')
    parser.add_argument('--conf-thres', type=float, default=0.25, help='TF.js NMS: confidence threshold')
    parser.add_argument('--include', nargs='+',
                        default=['onnx'],
                        help='available formats are (torchscript, onnx, coreml, saved_model, pb, tflite, tfjs)')
    opt = parser.parse_args()
    print_args(FILE.stem, opt)
    return opt

只能用在pt模型转onnx模型阶段，在其他时候不要增加这句代码  

self.training = True

    def forward(self, x):
        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()

            self.training = True
            if not self.training:  # inference
                if self.onnx_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)

                y = x[i].sigmoid()
                if self.inplace:
                    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
                else:  # for YOLOv5 on AWS Inferentia https://github.com/ultralytics/yolov5/pull/2953
                    xy = (y[..., 0:2] * 2 - 0.5 + self.grid[i]) * self.stride[i]  # xy
                    wh = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]  # wh
                    y = torch.cat((xy, wh, y[..., 4:]), -1)
                z.append(y.view(bs, -1, self.no))

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

使用到的库