How can I get the feature vector (the N-1 layer's output before softmax) of input image from deep model?

Question

How can I get the feature vector (the N-1 layer's output before softmax) of an input image from deep model? I am using Microsoft's CNTK deep learning toolkit.

score 3 · Answer 1 · answered Jan 12 '17 at 03:18

3

Here is an example that you may want to try out: https://github.com/Microsoft/CNTK/tree/master/Examples/Image/FeatureExtraction

answered Jan 12 '17 at 03:18

Sayan Pathak

870
4
7

How can I get the feature vector (the N-1 layer's output before softmax) of input image from deep model?

1 Answers1