violet-2422

anchor free 疑问

3

您好，最近在深深入研究这项工作，也很感谢您的巨大贡献，请问yolox这种anchor free机制在loss计算的时候如何确保浅层特征预测小目标而深层特征预测大目标的呢？

4.2. Modeling implicit knowledge question？

2

Hello, I was looking at your interesting work recently. When I saw Section 4.2, I had some questions. How is the 3 modeling methods reflected in the code?  I...

Flops不一样

2

  都是640输入怎么算力差这么多

Win11 can't connect

15

hello！My win11 computer is used as the client to join the host with the linux system as the manager. It is normal for me to join the network on win11,...

请问预训练模型选择哪个网络类型 

代码bug

6

我用原作者的pytorch2onnx导出onnx文件后，进行加载识别时出现以下错误 ``` Traceback (most recent call last): File "E:\MyWork\Yolo-FastestV2\dnn.py", line 112, in outputs = model.detect(srcimg) File "E:\MyWork\Yolo-FastestV2\dnn.py", line 91, in detect outputs[top:top + length, 0:2] = (outs[row_ind:row_ind + length, ValueError:...

I set plot to True, but don't display the images. Can't I run directly in PyCharm

The Weshmo Plot function does not refresh in real time during training

VGG_imagenet.npy

1

can not download VGG_imagenet.npy！ please help me!