How to understand Softmax layer activations for pretrained CNN?
2 views (last 30 days)
I was able to get softmax layer probabilities for the squeezenet network. Using
act1 = activations(net,i,'prob','OutputAs','rows');
However, Im unsure exactly what the probabilities represent, or how to identify what class they correspond with. Could you please explain what these probabilities mean? And how to get the corresponding class?
Jon Cherrie on 22 Apr 2021
How to identify what class they correspond with?
We can get this from the class names property of the output layer.
What these probabilities mean?
They are the probability that the given image is in the corresponding class.
Here's an example
net = squeezenet;
img = imread('peppers.png');
img = imresize(img,net.Layers(1).InputSize(1:2));
We can get the names of the classes from the output layer, which happens to bne the last layer for this network:
c = net.Layers(end).Classes;
Then get the activations from the softmax layer
p = activations(net,img,'prob','OutputAs','rows');
Note that these sum to 1
ans = single
We can then find the maximum probability and which class that corresponds to
[pm, i] = max(p)
pm = single
i = 946
ans = categorical
This is the same information that comes from the classify command:
[cc, pp] = classify(net,img);
cc = categorical
ans = logical