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

Quations reagrding Decoder #35

Open
prashant45 opened this issue Oct 2, 2020 · 1 comment
Open

Quations reagrding Decoder #35

prashant45 opened this issue Oct 2, 2020 · 1 comment

Comments

@prashant45
Copy link

Hi,

Thank you for an awesome, well-organized repository.
I have a question regarding the Decoder block. The paper states, they use a 1-D transposed convolution operation for the generating the decoder basis functions. paper
Screenshot from 2020-10-02 12-40-05

However, I see you use a linear dense layer in the decoder

Conv-TasNet/src/conv_tasnet.py

Line 126 in 94eac10

self.basis_signals = nn.Linear(N, L, bias=False)

Could you explain the reason for this choice?
@tky823
Copy link

tky823 commented Jan 2, 2021

linear dense layer overlap-add is the same as a transposed convolution.

Conv-TasNet/src/conv_tasnet.py

Lines 140 to 141 in 94eac10

est_source = self.basis_signals(source_w) # [M, C, K, L]
est_source = overlap_and_add(est_source, self.L//2) # M x C x T

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
@prashant45 @tky823