thestars-maker

weights

1

## ❔Question 可以分享一下训练好的权重吗？非常感谢 ## Additional context

In the model export using export.py export, don't use end2end,onnx the output dimension is float32[1,25200,85],, may I ask this 85 is such as refers to those dimensions it [boxes,prob,per classes...

?????

2

### Search before asking - [X] I have searched the YOLOv5 [issues](https://github.com/ultralytics/yolov5/issues) and found no similar bug report. ### YOLOv5 Component _No response_ ### Bug yeugaiyuelaiji ### Environment sss ###...

weights

2

Now,xview-yolov3 weights don't install, Can you give a new download address。

From the graph of your model results, does this count as co-training or something else?

How should I do onnx export and reason about it, is it possible to use only torch related methods without using detectron2?

two device

1

源代码 conv_weight = self.conv.weight conv_shape = conv_weight.shape conv_weight_hd = torch.cuda.FloatTensor(conv_shape[0], conv_shape[1], 3 * 3).fill_(0) conv_weight_hd[:, :, [0, 3, 6]] = conv_weight[:, :, :] RuntimeError: Expected all tensors to be on...