ethanhe42 / softer-NMS

Bounding Box Regression with Uncertainty for Accurate Object Detection (CVPR'19)

Home Page:https://github.com/ethanhe42/KL-Loss

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Final loss when you train your model

hding2455 opened this issue · comments

Hi I am trying to train a SSD using xxyy and KL loss. May I ask the final loss when you train your model using xxyy and KL loss? It seems location_loss can be a negative number, is that normal?

The loss can be a negative number. BTW, please have a look at our CVPR version code: https://github.com/yihui-he/KL-Loss
The performance is improved.