Closed tlkvstepan closed 6 years ago
From the deploy.tpl.prototxt
of flownetS in caffe code, line 893
layer {
name: "Eltwise4"
type: "Eltwise"
bottom: "predict_flow2"
top: "blob44"
eltwise_param {
operation: SUM
coeff: 20.0
}
}
Coeff is 20, meaning network is trained to output 1/20 of original flow. It is also consistent with pretrained weights of caffe network !
Clement
Thank you!
I am working with DispNetCorr1D model and it does not have this line..
DispNet output is indeed not multiplied by 20 (but it's not flow net 😉 ). Also, Correlation module is not avalaible for the moment in pytorch (if you have a functional solution for this, I'd be glad to add it to this repo !)
But I guess you can remove it pretty easily if you want, or just add the option --div-flow 1
to your command.
I am working with DispNetCorr1 with the end goal to re-implement CRL and I have my own repository (which is private right now), but I will be glad to contribute missing parts to yours.
That would be super cool ! Did you manage to get a working cuda layer of CRL ? I'm not much of a cuda guy so I did not even try to implement it :disappointed:
Hey, you might want to test this correlation module : https://github.com/NVIDIA/flownet2-pytorch/tree/master/networks/correlation_package
@ClementPinard thank you for the link. I will test it out and compare with pytorch cuda implementation (which is, I think, already quite fast).
Thank you again their project is amazing!
Hi @ClementPinard, i have a small question. Why do you normalize disparities / flows by std=20. Where did you find this in the original code? Thank you!