search

sunset1995 / pytorch-layoutnet

Pytorch implementation of LayoutNet.
MIT License
171 stars 39 forks source link

Why Eval with flip and rotation #15

Open robotshanxi opened 5 years ago

robotshanxi commented 5 years ago

It looks to me the network training has no flip or rotation, why they are added as evaluation? Thanks

sunset1995 commented 5 years ago

Hi, The network was actually trained with flip and rotation augmentation (see dataset.py).

robotshanxi commented 5 years ago

Thanks for the reply, I was thinking args.no_flip is true. My mistake.