Why do not use the predict value of Border network to help the segment result in DFN when in evaluation step?

yu-changqian / TorchSeg

Fast, modular reference implementation and easy training of Semantic Segmentation algorithms in PyTorch.

MIT License

1.41k stars 253 forks source link

Why do not use the predict value of Border network to help the segment result in DFN when in evaluation step? #58

Closed pdoublerainbow closed 5 years ago

pdoublerainbow commented 5 years ago

Hi, thanks for your open source. I have a question about why in the evalution step, you do not use the predict of Border network to help the segment result in DFN. I still have a question about if i want to use the predict of Border network to help the segment result, what should i do ? I can't figure out a prefect Strategy about this. I am looking forward to your reply, Thanks.

yu-changqian commented 5 years ago

In my future work, I am also attempting to utilize the prediction of Border Network to help the segmentation prediction.

pdoublerainbow commented 5 years ago

@ycszen Looking forward to your future work.

yu-changqian commented 5 years ago

Thanks. We can discuss it further~