ResNet-50

[Arsey]

Is it possible to have ResNet-50 for this approach?

[eldar]

Hi @Arsey, here it is:

http://datasets.d2.mpi-inf.mpg.de/deepercut-models/ResNet-50-mpii-multiperson.caffemodel http://datasets.d2.mpi-inf.mpg.de/deepercut-models/ResNet-50-test.prototxt

I'll keep the ticket open until I put the links in the repo.

[Arsey]

@eldar Thank you! BTW what's the test results does it have in comparison to ResNet-152?

[leonid-pishchulin]

have a look in the deepercut paper, there is a unary evaluation table with resnet 50, 101 and 152.

⁣-Leonid​

On Jun 29, 2017, 11:02 PM, at 11:02 PM, Alexander Lazarev [email protected] wrote:

@eldar Thank you! BTW what's the test results does it have in comparison to ResNet-152?

-- You are receiving this because you are subscribed to this thread. Reply to this email directly or view it on GitHub: https://github.com/eldar/deepcut-cnn/issues/16#issuecomment-312182882

[Arsey]

Oh, yes I've forgotten about that table. Thanks!

[oujieww]

how to use it on mulit person