liushuai839

关于训练

7

你好,翔哥,首先感谢你的工作.在我训练的过程中,出现了这样的问题: 我分别训练GFLv1 和 GFLv2, 发现刚开始的分类损失相差很大, GFLv1的分类损失在0.4~0.5左右,但是GFLv2的分类损失直接变成了700-800之间,我想问下这是一个正常的现象吗? 你在训练的时候遇到过吗

compile error

1

Hi,author When I compile the program with code: python test/nms/test_nms.py I met a error: ImportError: /home/liushuai/STUDY/MyWorkSpace/object_detection_test/easy-faster-rcnn.pytorch-master/support/_C.cpython-36m-x86_64-linux-gnu.so: undefined symbol: _ZN3c105ErrorC1ENS_14SourceLocationERKSs How can I solve it? I hope you can give me...

some question about focal loss in code

2

Hi,Guys! When I read the code, I found a problem that the two inputs of focal loss ,which are cls_pred an label , the dimension of them is not the...

some questions about the structure of cornerNet-saccade

1

Hi,Guys: Thanks for your code, I have some questions about the structure of cornerNet-saccade. In the paper, it says that the you will use the attention map to get the...

some questions about centers in corner-xnet

1

Hello, guys, I am confused about why regressing the centers directly in corner-xnet can replace the embeddings in cornerNet to do the corner matching ?