heimayouxia
heimayouxia
@qfgaohao May I asked how many epochs have you trained your pre_trained vgg16-ssd model? It is fairly accurate. But I can't achieve the comparable mAP on my custom dataset no...
@sunwell1994 @zgq91 Same issue here on my custom dataset. I have tried the training strategy as @dmatos2012 's suggested. It barely helps. Loss still drops dead slow while mAP is...
> Let me see if I can find some time in the comming holiday. lying_face As much as the respect I come to pay, I would love to study the...