search

kevinlin311tw / Caffe-DeepBinaryCode

Supervised Semantics-preserving Deep Hashing (TPAMI18)
https://arxiv.org/abs/1507.00101v2
Other
205 stars 83 forks source link

softmax in cifar10 #15

Closed AlanZhangv1 closed 6 years ago

AlanZhangv1 commented 7 years ago

hi Kevin,I have a problem about the softmax loss function in CIFAR10 dataset.It seems that you don't use softmax to predict the probility for every class ?and direct use the fc9 outputs to calculate the accuracy?

kevinlin311tw commented 7 years ago

We use softmax to predict the probability. In the testing (or validation) phase, we use the accuracy layer in caffe which help us compute the probability as well as evaluate the classification accuracy.