yjh0410 / new-yolov1_pytorch Goto Github PK

The file generated in the folder : "voc_eval" is not available , and the error is File was loaded in the wrong encoding : 'UTF-8' , I've tried every encoding ,but the problem still exist
how can I solve this problem?
thanks!

Hi, Can you please share the weights in either Google Drive or Dropbox. It would be really helpful

你这个预测头为什么最后通道数是25？不应该是30么

我看了一下原版的论文， 加了CBAM 后代码很多人train效果还不如原版的resnet50。
请问一下作者有没有去掉SAM模块试过呢？效果如何?

Hi! Thanks for awesome work!
Recently, I am trying to design a new object detection network based on yolov1, my work is based on another work https://github.com/abeardear/pytorch-YOLO-v1/blob/master/train.py . I have tested that my work can overfit in Pascal VOC 2007+2012 trainval. But my work suffered heavy overfit . I have tried dropout weight decay and data augment . But the problem is still not solved. And I noticed your work , I find that you will do a normalize to image which is other work doesn't have . Why you do it? Is is have an advantage in overcoming overfit?
Looking forward to your reply!

我目前的做法是去掉了VGG16的classifier，然后在yolomodel中将stride改为69，这样标签的维度就变成了6，6，25，但是在预训练的vgg16的基础上，只能跑到58.76，而baseline为66.4，请问我该怎么修改代码得到baseline？

init() got an unexpected keyword argument 'mosaic'，我自己在所有文件目录下都未找到mosaic

这是yolov1还是yolov2
This is yolov1? yolov2?