-
Notifications
You must be signed in to change notification settings - Fork 1.3k
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
Potentially redundant bias in convLSTM #65
Comments
lcnature
changed the title
Potentially redundant bias
Potentially redundant bias in convLSTM
Sep 27, 2017
diegolascasas
pushed a commit
that referenced
this issue
Jul 31, 2018
#65 PiperOrigin-RevId: 202473272
Fixed as of e15eb74 - the old behaviour is still the default as we want to maintain checkpoint compatibility, but setting |
aisuperdev
added a commit
to aisuperdev/sonnet
that referenced
this issue
May 30, 2022
google-deepmind/sonnet#65 PiperOrigin-RevId: 202473272
anatoliinzrnk
added a commit
to anatoliinzrnk/sonnet
that referenced
this issue
Sep 10, 2024
google-deepmind/sonnet#65 PiperOrigin-RevId: 202473272
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
https://github.com/deepmind/sonnet/blob/7da90b8e63fb684b91a12e1e9a42999962804e3a/sonnet/python/modules/gated_rnn.py#L1129
Hi, I realized that the variable of convLSTM includes two biases if
use_bias
is set to true. And I think it is because here the convolution is performed separately on input and state. But effectively only one set of bias is necessary. Perhaps adding bias at the end instead of within the convolution as done in the tensorflow contrib version (https://github.com/tensorflow/tensorflow/pull/8891/files) would be better.The text was updated successfully, but these errors were encountered: