Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

question about fully connected layers #1

Open
Jee-King opened this issue Jun 24, 2019 · 0 comments
Open

question about fully connected layers #1

Jee-King opened this issue Jun 24, 2019 · 0 comments

Comments

@Jee-King
Copy link

Hi, thanks for sharing your works.
I have two questions

  1. inputTensor = inputTensor - 128, why do you subtract 128?
  2. The whole project seems using different datasets of different tasks to train. That means, you just mixes the datasets together and then trains the whole， train_loss_all has no practical use.
    What is the role of 20 fully connected layers?
    Looking forward to your reply.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@Jee-King