search

kuangliu / pytorch-retinanet

RetinaNet in PyTorch
992 stars 250 forks source link

Train loss is decreaing while validation loss is increasing #29

Closed prakashjayy closed 6 years ago

prakashjayy commented 6 years ago

Hi,

The train loss is decreasing with each epoch and validation loss is increasing and becoming stagnant after sometime.

Can u put up some results on VOC datasets. so that we can cross check ?

Thanks