How to understand Softmax layer activations for pretrained CNN?

2 visualizzazioni (ultimi 30 giorni)
AK il 21 Apr 2021
Commentato: AK il 27 Apr 2021
Hello,
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?
Thank you!
0 CommentiMostra -2 commenti meno recentiNascondi -2 commenti meno recenti

Accedi per commentare.

Risposta accettata

Jon Cherrie il 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 = 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
sum(p)
ans = single
1
We can then find the maximum probability and which class that corresponds to
[pm, i] = max(p)
pm = single
0.4172
i = 946
c(i)
ans = categorical
bell pepper
This is the same information that comes from the classify command:
[cc, pp] = classify(net,img);
cc
cc = categorical
bell pepper
isequal(pp, p)
ans = logical
1
4 CommentiMostra 2 commenti meno recentiNascondi 2 commenti meno recenti
AK il 22 Apr 2021
Yes! This is perfect! Thank you!
AK il 27 Apr 2021
How do i get the probability of a particular index (i) ? As in, I know the index and want the associated probability. Thanks!

Accedi per commentare.

Categorie

Scopri di più su Image Data Workflows in Help Center e File Exchange

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by