about matcaffe_batch_feat

[kli017]

I have a question about the extracted feature.
I read the code of matcaffe_batch_feat and found that you did not give a certain layer to extract the features just like the example in caffe. So my question is did you directly extract features from the last sigmoid layer? is the feature a 1 by 48 vector?

[kevinlin311tw]

Sure. We remove the classification layer in the deploy file. 2017-09-05 6:47 GMT-07:00 Kai <notifications@github.com>:

…

I have a question about the extracted feature. I read the code of matcaffe_batch_feat and found that you did not give a certain layer to extract the features just like the example in caffe. So my question is did you directly extract features from the last sigmoid layer? is the feature a 1 by 48 vector? — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub <#24>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AJgtMDD0CzKcfvR1tz6nwGGXKYZRfpjTks5sfVD9gaJpZM4PM-Wi> .

-- Best regards, 林可昀 Kevin Lin

[kli017]

cool thank your for the reply 👍