Diogo Falcao

Facing the same issue with the new release of Jupyter Lab, version at 1.1.0

About the DeepID2, in your implementation you use: "layer { name: "simloss" type: "ContrastiveLoss" loss_weight: 0.00001 contrastive_loss_param { margin: 0 } bottom: "pool5" bottom: "pool5_p" bottom: "label1" bottom: "label2" top:...

@denghuiru What are the values that you are using on the solver? Thank You

@denghuiru you got any improvements doing what you suggest? You were able to make the network to converge, using a valid constrative loss?

@denghuiru Yeah, sure. I am still trying to converge the network on training, but if I got any progress I will post here

@denghuiru I got some ideas from a discussion list in the caffe users. I will try to do the follow: I created 3 diferents prototxt and try to execute them...

By the way, if we could train the DeepID2 (my network are still training now), how do we get the output vector for one image? Should we get the combination...

@happynear I found a problem with your caffe version, I am using your windows version (caffe repository) but it seens that you don't have the last version for the constrative...

Same problem.

Hey, I am also very interested in this feature, there is any news about this? how can I help? @lix-mms