Added DropConnect Layer and its tests.Fixes #413 #552
Closed
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
In drop_connect_layer.hpp, we randomly drop weights instead of units.This layer is based on linear_layer.hpp, with the exception that the weights matrix is multiplied by the mask.
|
@zoq I've added drop connect layer and also the tests. And the tests are passing on my system.Can you tell if any changes are required. |
|
@abhinavchanda, The code that you have written is only for a linear layer. This needs to be generalized. |
|
Merged DropConnect implementation; take a look at #576. |
|
thanks for the reply. |
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Outdated suggestions cannot be applied.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.
DropConnect Layer is based on Linear Layer, but with the difference that the weight matrix is multiplied by the random mask.I have also added tests, in which , the network architechture and size of hidden layer is same as that of the dropout layer in tests/feedforward_network_test.cpp.On my systems, the three tests are giving these classificationErrors:
Dropout DropConnect
1 0.0729288 0.0729288
2 0.02 0.02
3 0.134 0.068