Object detection and Semantic segmentation

[abhigoku10]

@vandit15 thanks for open-sourcing the code , is it possible to use Cb loss in the object detection or segmentation architecture ?? did you experiment it with any std architecture as yolo retina, deeplab ?? since i am planning on using to our custom object detection architecture so

[jiawen7777]

I have the same question, I have implemented it on SSD and the loss works, If I need to do six categories classification, my category number would be seven because there is one more 'background' class. But I couldn't get the number of samples of this class. I am so confused