search

ClementPinard / SfmLearner-Pytorch

Pytorch version of SfmLearner from Tinghui Zhou et al.
MIT License
1.01k stars 224 forks source link

explainability mask should be softmax? #62

Closed sohamghosh121 closed 5 years ago

sohamghosh121 commented 5 years ago

In the original repo, and the paper models the explainability mask as a softmax https://github.com/tinghuiz/SfMLearner/blob/2a387b763bc2b6f95b095f929bf751797c9db68a/SfMLearner.py#L83 https://github.com/tinghuiz/SfMLearner/blob/2a387b763bc2b6f95b095f929bf751797c9db68a/SfMLearner.py#L151

Whereas you have sigmoids, and BCE https://github.com/ClementPinard/SfmLearner-Pytorch/blob/0f741cb06caa3fbc95f487187697e54d2e03c190/models/PoseExpNet.py#L83

Is this intentional? DId sigmoid work better?

sohamghosh121 commented 5 years ago

Sorry, I realised the original paper is slightly weird - it outputs 2 channels for each mask (I thought softmax over pixels), and takes softmax across channels. So this is not exactly equivalent, but probably better.

ClementPinard commented 5 years ago

It's actually strictly equivalent. the softmax of a 2 channel tensor is actually the sigmoid of the difference between the two channels.

Besides, BCE is the cross entropy when you only have 2 channels. Since in that context, only knowing one chanel is enough to know everything, you only need to feed it one channel.

So this is intentionnal, it doesn't work better, but it's certainly much more readable that way.