why the loss not converge?
daiwc opened this issue · 2 comments
daiwc commented
I used the Gaussian_yolov3_KITTI_3cls to train a new model without using pretrained model, the loss still around a hundred after 10000 iterations.
jwchoi384 commented
@daiwc
Hello, please see the link below.
I have already explained this issue elsewhere.
#19 (comment)
#54 (comment)
daiwc commented
thanks a lot!
…------------------ 原始邮件 ------------------
发件人: "Jiwoong Choi"<notifications@github.com>;
发送时间: 2020年2月12日(星期三) 下午4:32
收件人: "jwchoi384/Gaussian_YOLOv3"<Gaussian_YOLOv3@noreply.github.com>;
抄送: "戴伟聪"<493980892@qq.com>; "Mention"<mention@noreply.github.com>;
主题: Re: [jwchoi384/Gaussian_YOLOv3] why the loss not converge? (#57)
@daiwc
Hello, please see the link below.
I have already explained this issue elsewhere.
#19 (comment)
#54 (comment)
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub, or unsubscribe.