-
Notifications
You must be signed in to change notification settings - Fork 276
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.
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
Passing a video to S4ND #146
Comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Hello,
My question might seem too naive but I'm confused by the arguments passed to the S4ND model (dim, d_model, d_state, channels, out_channels, d_output, ...) and the expected input shape.
Assume I have a video of shape (batch_size, nb_frames, nb_channels, height, width) = (1, 30, 3, 128, 128), how should I reshape the video to pass it to the S4ND model, and what arguments of the model should be adjusted accordingly?
Also, if the desired output is a sequence of labels of length=nb_frames (so that each image in the video will get a label), which argument should be adjusted? d_output or out_channels or...?
I would highly appreciate your prompt response.
The text was updated successfully, but these errors were encountered: