About provided component dictionaries and VGG 19 weights file

[csxmli2016]

About provided component dictionaries and VGG 19 weights file

[csxmli2016]

Hi.

I want you ask about component dictionaries and vgg 19 weights file that you provided.

which resolution of images are used for training?? is it 256 x 256 or 512 x 512 ??

In the paper, for handling 256 x 256 images, left/right eyes, nose and mouth on scale-1 are set to 40/40, 25, 55 respectively. So I think 256 x 256 resolution images are used for training.
But the provided model is making 512 x 512 resolution image.
I'm just wondering about that.
Thank you in advance :)

We trained two models, i.e., 256 and 512. The 512 model has more application values, so we only release this one.

[SongDoHou]

Thanks.

So it means that component dictionaries are made with 512 x 512 resolution images??

[csxmli2016]

Thanks.

So it means that component dictionaries are made with 512 x 512 resolution images??

Obviously, 256 model conducted the dictionary on 256 images, 512 model on 512 images.

[SongDoHou]

Thank you for the information.
Could you provide pretrained model for 256 x 256 resolution ??

[csxmli2016]

Thank you for the information.
Could you provide pretrained model for 256 x 256 resolution ??

Hi, we just release the 512 model to show its effectiveness on visual performance and did not plan to release others.