Giters

xiaoyufenfei / Efficient-Segmentation-Networks

Lightweight models for real-time semantic segmentationon PyTorch (include SQNet, LinkNet, SegNet, UNet, ENet, ERFNet, EDANet, ESPNet, ESPNetv2, LEDNet, ESNet, FSSNet, CGNet, DABNet, Fast-SCNN, ContextNet, FPENet, etc.)

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

ENet prediction become worse after 100 epoch

guanqp opened this issue · comments

commented

I use this project to train ENet on cityscapes dataset(640*480). The loss decase normally, but predict result become worse when trainning for more than 50 epochs...
image
from left to right, 10epoch, 50epoch, 80epoch.
and the training loss vs epochs looks fine:
image

Can anyone give me some advice? Thanks!

commented

Looks like the train process does not evaluate the validation loss and mIoU, so the model over fited.