Enable skip biases in Conv3dLayer, the same as beta and gamma in BN Layer #421
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
update from upstream
zsdonghao
reviewed
Mar 16, 2018
tensorlayer/layers/normalization.py
Outdated
| beta_init : initializer or None | ||
| The initializer for initializing beta, if None, skip beta | ||
| gamma_init : initializer or None | ||
| The initializer for initializing gamma, if None, skip gamma |
There was a problem hiding this comment.
Tell users when we will need to skip beta and gamma here.
.rst link format:
`link <http://.....>`__
zsdonghao
approved these changes
Mar 17, 2018
luomai
pushed a commit
that referenced
this pull request
Nov 21, 2018
…ayer (#421) * update by lllcho on March 15 * update logging * b_init in c3d can None and gamma/beta in BN layer can skip * fix some comments * add comments in bn layer
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Enable skip biases in Conv3dLayer to keep consistent to Conv2dLayer, which is useful when inflate 2D ImageNet pretrained model to C3D model. In some case, we also need skip the gamma/beta in BN layer, such as the inception_resnet_v2 model, the gamma is ignored.