search

knazeri / edge-connect

EdgeConnect: Structure Guided Image Inpainting using Edge Prediction, ICCV 2019 https://arxiv.org/abs/1901.00212
http://openaccess.thecvf.com/content_ICCVW_2019/html/AIM/Nazeri_EdgeConnect_Structure_Guided_Image_Inpainting_using_Edge_Prediction_ICCVW_2019_paper.html
Other
2.52k stars 532 forks source link

Question about Places2 Dataset #49

Closed jingyuanli001 closed 5 years ago

jingyuanli001 commented 5 years ago

Hi, thanks you for your amazing work and contribution to the field. I'm very interested in your work and I'm currently trying to reproduce the result in places2 dataset. I noticed that there exists 2 parts in places2 which is the standard one and the places2 challenge one. So I would like to know which part(s) did you use for training your model. :)

knazeri commented 5 years ago

@JensonLLL We used the full places2 dataset which contains roughly 8 million images! But that dataset is huge and it takes a very long time to train! If I'm not mistaken, the standard version contains almost 1.8 million images which is also large enough to capture the natural scene data distribution. Having said that, if you have the computational resources and time(!) then go for the places2 challenge one :D