search

kevinlin311tw / Caffe-DeepBinaryCode

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

Confuse about the figure #3

Closed sunyinhui closed 8 years ago

sunyinhui commented 8 years ago

What is the number of red dot in the last layer??? the number of green dot is one??? or not ?? what is the meaning of that??? Thanks very much!!! numbers

sunyinhui commented 8 years ago

image I can get the message. please help me

kevinlin311tw commented 8 years ago

Hi @sunyinhui Sorry. Since this project is a work in progress, some parameter names may confuse. We will improve this as soon as possible.

The red and green parts represent two different objective functions. They are not layers, so they don't have "nodes". The green one represents the K1_EuclideanLoss, and the red one is K2_EuclideanLoss. K1_EuclideanLoss will enforce each node in encode_neuron to be 0 or 1. K2_EuclideanLoss will ensure each node in encode_neuron has a 50% chance of being 0 or 1.

Btw, our binary codes are learn in the encode_neuron. During testing, we extract the binary codes from encode_neuron

Should you have any question about the paper, please feel free to email me.

sunyinhui commented 8 years ago

Oh , Thanks! ^_^

sunyinhui commented 8 years ago

Hi Kevinlin，I can not underdtand deeply the loss_beta and loss_gamma . Please help me. Thanks