Model details different from original paper

[weishuanglong]

Hi there,

I read the original paper and this implementation, and that's awsome!

However, I have a question concerning the details of SSTD net, and I'm really looking forward to see you reply:)

(1) In the deconvolution part, I see that you use groups=64 to upsample. But generally speaking, groups=1 might be more reasonale, so I guess it's for saving computational complexity? Or is there any other reasons?

(2) The original paper uses deconv3_3, conv1_1 to establish attention map. I see that you're using deconv16_16 and two conv3_3 to do it. Does it mean that this implementation is better than that in the original paper?

It's a very nice code and I really appretite your comment!

Thanks

[BestSonny]

@weishuanglong Thank you for the questions.

(1). Yes. You can also try to use groups=1 to see the difference. I am not familiar on this part. I find one interesting paper shuffle-net on these discussions.
(2). I would say this part is not so important. I do not observe much difference on the performance.