I am developing face recogniser and in my data set there are 3000 different people each having around 40 different pictures. My question is, will my output layer have 3000 different classifications.

Views: 390

Reply to This

Replies to This Discussion

Ideally Yes, as you are trying to predict 3000 different classes (or people in your case). Your output layer should use "softmax" activation which will give you a probability of which class each input image belongs to.

Take a look at this very cool in-browser demo implementation of a CNN which classifies hand-written digit images. It may help you understand how the different layers work in sync with each other


Hope it helps...


© 2021   TechTarget, Inc.   Powered by

Badges  |  Report an Issue  |  Privacy Policy  |  Terms of Service