LF-InterNet icon indicating copy to clipboard operation
LF-InterNet copied to clipboard

Question about the pretrained models

Open ZhengyuZhang96 opened this issue 3 years ago • 2 comments

Hi, author. I really appreciate your interesting work! But I would like to know which dataset is used to train the pretrained models that you provide? or you train the model with all the data in 6 datasets?

looking forward to your reply!

ZhengyuZhang96 avatar Apr 21 '21 16:04 ZhengyuZhang96

Thanks for your attention to our work. The pretrained models in this repo were trained using all the 6 datasets as mentioned in the ECCV paper. We also released the pretrained models trained on the first 5 datasets (exclude STFlytro) in our LF-DFnet repo. We suggest to use the first 5 datasets for training and test since the STFlytro dataset has a very large number of Lytro scenes and can degrade the performance of algorithms on the HCI and STFgantry datasets.

YingqianWang avatar Apr 23 '21 08:04 YingqianWang

Thanks for your reply!

ZhengyuZhang96 avatar Apr 26 '21 04:04 ZhengyuZhang96