jinyeying/FogRemoval

Training Setting Question

cuiziteng opened this issue · 2 comments

Thanks for the nice work.

I'm confuse about the training setting in paper, which dataset have you use to first "pre-train" the model?

And then use the "pre-train" weights to fine-tune on various dehazing dataset (like the smoke dataset)? Am I understand right ?

Hope to get your reply! Thx ~

Thanks for the nice work.

I'm confuse about the training setting in paper, which dataset have you use to first "pre-train" the model?

And then use the "pre-train" weights to fine-tune on various dehazing dataset (like the smoke dataset)? Am I understand right ?

Hope to get your reply! Thx ~

yes, we use Fig. 7 and Fig. 8 in the supply to first "pre-train", then fine-tune on each datasets.

Thanks for the explanation, I'll follow that setting.