Marcel Simon

Hi! There is a pooling in both my and Kaiming's implementation. I can't see what you mean. Could you please provide line numbers for both prototxts?

I see, thanks a lot for pointing that out! The difference occurs only at the first expand layer, the other ones are correct. The batch norm, scale and relu is...

The implementation you are referring to is the original ResNet, not the preactivation variant. Please see https://github.com/facebook/fb.resnet.torch/blob/master/models/preresnet.lua and https://github.com/KaimingHe/resnet-1k-layers/blob/master/resnet-pre-act.lua#L63 for the preactivation variant

Which ResNet implementation are you using? Usually VGG is smaller than ResNet-50, and hence also much smaller than ResNet-101 also for such a large input size. What is the batch...

This kind of resolution (>1000px) is too high for a VGG19 with Batch Normalization in caffe. If you really want to train with this image size, you should merge the...

Hi! Which model are you using? Multi GPU shouldn't make a difference for VGG or AlexNet, but can make a difference for ResNet. For ResNet, please make sure that each...

It seems there was a problem with creating a repository. Maybe it already exists in gogs? The ValueError seems to occur when printing the error message, not sure why this...

The script focuses on cloning repositories, wiki and user info are not touched. Am 30. Oktober 2018 05:52:24 schrieb cpetry : > Hi there, > Does this also migrate issues...

I didn't have this problem. You can try replacing the parfor loops by regular for loops for easier debugging.

In case anybody gets the same error, you may use my fork at https://github.com/MarcelSimon/ibot which fixes this issues and also provides a docker image to make it easier to run...