Oisin Mac Aodha
Oisin Mac Aodha
Hi there, I really like the paper and was wondering if you tried training a linear SVM on your 128 dim feature space - and if so how will did...
Hi there, This is a bit of a meta-question. I noticed that your [code](https://github.com/HobbitLong/CMC/blob/master/models/alexnet.py#L25) uses the original AlexNet parameters i.e. with convolutions 96,256,384,384,256 vs. the one weird trick paper 64,192,384,256,256...
Hi there, These datasets look really great. I was wondering if you had an estimate of the quality of the individual IDs in the test set? Are they close to...