-
Notifications
You must be signed in to change notification settings - Fork 18.7k
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
Dummy data layer #480
Dummy data layer #480
Conversation
This great Jeff, I have something similar for net_speed but this is more general. On Sunday, June 8, 2014, Jeff Donahue notifications@github.com wrote:
Sergio |
Nice layer and short and to the point implementation. Please add the GPU version then rebase since #479 was rewritten. Feel free to merge yourself once that's done! This is great otherwise. |
Dummy data layer
This is a layer that outputs "dummy" data from a
Filler
, e.g.ConstantFiller
orGaussianFiller
to an arbitrary number of blobs of arbitrary sizes. It takes N >= 1 top blobs, 1 or Nnum
s,channels
s,height
s, andwidth
s and 0, 1, or Ndata_filler
s. If there are 0data_filler
s, output all 0s to all top blobs. If there is exactly 1 of any ofnum
,channels
,height
,width
,data_filler
, that value is used for all top blobs. If there are exactly N of any ofnum
,channels
,height
,width
,data_filler
, use the ith value for the ith top blob.For any
ConstantFiller
s, the data is filled duringSetUp
and never touched again inForward
. For all other filler types (all of which output random data), the data is filled on each iteration usingForward
.I can think of a couple use cases for this, including:
unit tests for an entire net where one might not want to create an entire temporary LevelDB (I use it for this purpose in later private commits, to be publicized soon).
regularization by use in combination with an
EltwiseLayer
(withop == SUM
) to add random (e.g., Gaussian) noise to data in some layer of the net.