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 on Weight Calculation #2

Open
SashankMLAI opened this issue Nov 28, 2019 · 1 comment
Open

Question on Weight Calculation #2

SashankMLAI opened this issue Nov 28, 2019 · 1 comment

Comments

@SashankMLAI
Copy link

SashankMLAI commented Nov 28, 2019 •
edited
Loading

In the paper, it is mentioned that the model uses 300k parameters but according to my calculation, you just used 7 conv1d layers kernel size = 55 and filters = 30. Isn't total parameters = 7 * 30 * 55 + 55 (in the last layer). Which sums up to 11000 weights approx?
Am I missing something? please guide.
@JasonSWFu
Copy link
Owner

There are 30 channels in each layer (except for the input and output layer), so the number of weights should be roughly multiplied with 30.

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
2 participants
@JasonSWFu @SashankMLAI