You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
This repository was archived by the owner on Jul 10, 2021. It is now read-only.
Hi,
I'm trying out your (lovely) package on non image data, and would like to try using convolutions - I see that currently only 2D convolutions are supported, any chance of adding in 1D support/for non image/square data?
(i.e As my first layer I tried:
Convolution("Rectifier", channels=32, kernel_shape=(1,1))
)
'AssertionError: Input array is not in image shape, and could not assume a square.'
1D convolutions work already, there's a test for it. The problem here is that you want to apply the convolution over a 2D image but you're giving the NN a 1D array, and it can't figure out what size you mean. (It tries to guess square, but your data is not square.)
Try reshaping your inputs?
EDIT: In case you want to convolve over a 1D image, you still need to specify either (N, 1) or (1, N) as an array size—just like the kernel you have is 2D.
I am using a 1d array of features.. ;
So, The solution is to reshape the features (X) into a square? Ok, thanks.
On Jun 28, 2015 2:33 PM, "Alex J. Champandard" notifications@github.com
wrote:
1D convolutions work already, there's a test for it. The problem here is
that you want to apply the convolution over a 2D image but you're giving
the NN a 1D array, and it can't figure out what size you mean.
Try reshaping your inputs?
—
Reply to this email directly or view it on GitHub #96 (comment)
.
Activity
alexjc commentedon Jun 28, 2015
1D convolutions work already, there's a test for it. The problem here is that you want to apply the convolution over a 2D image but you're giving the NN a 1D array, and it can't figure out what size you mean. (It tries to guess square, but your data is not square.)
Try reshaping your inputs?
EDIT: In case you want to convolve over a 1D image, you still need to specify either
(N, 1)
or(1, N)
as an array size—just like the kernel you have is 2D.ddofer commentedon Jun 28, 2015
I am using a 1d array of features.. ;
So, The solution is to reshape the features (X) into a square? Ok, thanks.
On Jun 28, 2015 2:33 PM, "Alex J. Champandard" notifications@github.com
wrote:
alexjc commentedon Jun 28, 2015
If you have a
(1,1)
kernel you can use any input shape as long as it's 2D!ddofer commentedon Jul 17, 2015
By "N", do you mean a string input, or an integer with a preset size?
alexjc commentedon Jul 18, 2015
I mean an integer with preset size that matches your data.
elenacuoco commentedon Aug 11, 2015
Hi,
I have the same request. Your package is really useful. I did not understand how to use conv1D in your package. I'm looking for something like Conv1D in Lasagne (http://lasagne.readthedocs.org/en/latest/modules/layers/conv.html),without reshaping the data...
alexjc commentedon Aug 12, 2015
I will have to look at this and add a test or two. Thanks for the feedback!
alexjc commentedon Nov 20, 2015
We use Lasagne now, I'd consider adding this if there's enough interest!