make bias optional in dense layer #1314
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
|
Since |
|
changed bias type back to AbstractArray |
| end | ||
|
|
||
| @functor Dense | ||
|
|
||
| function (a::Dense)(x::AbstractArray) | ||
| W, b, σ = a.W, a.b, a.σ | ||
| σ.(W*x .+ b) | ||
| typeof(b) <: Zeros ? σ.(W*x ) : σ.(W*x .+ b) |
There was a problem hiding this comment.
I would prefer not to change the forward pass here, Zeros would be handled appropriately
| @@ -112,15 +115,15 @@ end | |||
| Dense(W, b) = Dense(W, b, identity) | |||
|
|
|||
| function Dense(in::Integer, out::Integer, σ = identity; | |||
| initW = glorot_uniform, initb = zeros) | |||
| return Dense(initW(out, in), initb(out), σ) | |||
| initW = glorot_uniform, initb = zeros(out)) | |||
There was a problem hiding this comment.
It's odd that here we have a function for weight and a vector for bias.
The more appropriate constructor would accept both weight and bias as kwargs ( refer the conv layers)
|
bump |
|
Replaced by #1379 I think. Perhaps we should still kill the |
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Outdated suggestions cannot be applied.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.
This is to make the bias in dense layer as optional parameters as in the convolution networks by using Flux.Zeros()
PR Checklist
@dhairyagandhi96(for API changes).