Added managing of PReLU layers #16
Open
Conversation
This file contains 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
It's now possible to correctly extract the weights from Caffe's PReLU layers and have them ready to be loaded onto a Keras model. Also, unknow layer types eventually encountered will be printed at the end of computation if flag --verbose is set
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Outdated suggestions cannot be applied.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.
It's now possible to correctly extract the weights from Caffe's PReLU layers and have them ready to be loaded onto a Keras model.
Caffe stores one parameter for each neuron in PReLU layers, and it's used for every activation in that neuron. Keras, instead, has one parameter for each activation.
So I extract one neuron's parameter and copy it once for each activation.
As result, we have that all activations of the same neuron have the same parameter value.
Also, unknow layer types eventually encountered will be printed at the end of computation if flag --verbose is set.