Dmytro Mishkin

Speaking about accuracy, this could be used as baseline: https://github.com/BVLC/caffe/wiki/Models-accuracy-on-ImageNet-2012-val

Hi, What is the image size you are working on? Could you post the problematic image here?

Might be it has some problems during generation. Try to delete the file and generate it again.

Well, I don`t like activations which could not be done "in-place", but if SReLU will be implemented in caffe, I test it.

@Darwin2011 Thank you! I can see two ways you can help: 1)Do your own benchmark and make PR like @dereyly done. 2)In caffenet-style networks, the real bottleneck, as I recently...

@bhack thanks, as usual ;)

@bhack yes, I have contacted that guy :) Now testing ResNet101 (as in paper, + without scale/bias, + without BN) without last block, because activation size is too small for...

@1adrianb there is even one successful attempt here https://github.com/ducha-aiki/caffenet-benchmark/blob/master/ResNets.md But at the most my trials, they overfit a lot. Which probably means that 128 px is not enough for them....

@1adrianb I use it...sometimes. Here are tests of the batchnorm and some of them use scale bias, while others not. Reason - test them all :) https://github.com/ducha-aiki/caffenet-benchmark/blob/master/batchnorm.md

Now vgg16 with all tricks is in training (to check if they for weaker models only)