AntiPrivateBus

Results 2 comments of AntiPrivateBus

> # Description > tl;dr: The pre-trained SSD checkpoint has a huge loss while training on the **VOC2007 train + val** dataset and it doesn't seem to be anywhere near...

> I think you guys get good results.Many others' losses are around 40,however,they gain high mAP in evaluation.So I think it doesn't matter whether loss is high when we get...