TomTomTommi / DeepMIH

Official repository of "DeepMIH: Deep Invertible Network for Multiple Image Hiding", TPAMI 2022.
121 stars 12 forks source link

your training set #2

Open kerryhhh opened 2 years ago

kerryhhh commented 2 years ago

Hi! Thank you for sharing your code! I found that the training set of your model in your paper uses the DIV2k dataset, but the training set of this dataset has only 800 images. I want to determine whether the pre-trained model you provided only uses these 800 images for training?

TomTomTommi commented 2 years ago

Hi, thanks for your interest. The pre-trained model is trained on DIV2K and finetuned on the COCO dataset. BTW, there seems to be no apparent gain during finetuning.