Skip to content
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

Write padding aware im2col? #36

Closed
mavenlin opened this issue Jan 18, 2014 · 5 comments
Closed

Write padding aware im2col? #36

mavenlin opened this issue Jan 18, 2014 · 5 comments

Comments

@mavenlin
Copy link
Contributor

@Yangqing Is there any specific reason for an individual padding layer but not supporting padding in im2col? My concern is that the padding layer causes unnecessary extra memory usage which can be avoided. Is it necessary to implement padding aware im2col function?

@Yangqing
Copy link
Member

Yangqing commented Feb 3, 2014

Just legacy reason, I guess... I was translating codes quickly from decaf to caffe and did not worry too much about memory consumption back then. Yeah, it would be good to have a padding aware im2col function to save a (rather unnecessary) copy of the data.

@sguada
Copy link
Contributor

sguada commented Feb 3, 2014

It would be even better to have a more memory efficient convolutional layer
that won't require im2col, but that it is going to be harder.

Sergio

2014-02-03 Yangqing Jia notifications@github.com:

Just legacy reason, I guess... I was translating codes quickly from decaf
to caffe and did not worry too much about memory consumption back then.
Yeah, it would be good to have a padding aware im2col function to save a
(rather unnecessary) copy of the data.

Reply to this email directly or view it on GitHubhttps://github.com//issues/36#issuecomment-34001933
.

@Yangqing
Copy link
Member

Yangqing commented Feb 3, 2014

I assume Forrest is working along that direction (not sure).

Yangqing

On Mon, Feb 3, 2014 at 1:40 PM, Sergio Guadarrama
notifications@github.comwrote:

It would be even better to have a more memory efficient convolutional layer
that won't require im2col, but that it is going to be harder.

Sergio

2014-02-03 Yangqing Jia notifications@github.com:

Just legacy reason, I guess... I was translating codes quickly from decaf
to caffe and did not worry too much about memory consumption back then.
Yeah, it would be good to have a padding aware im2col function to save a
(rather unnecessary) copy of the data.

Reply to this email directly or view it on GitHub<
https://github.com/BVLC/caffe/issues/36#issuecomment-34001933>
.

Reply to this email directly or view it on GitHubhttps://github.com//issues/36#issuecomment-34003395
.

@sguada
Copy link
Contributor

sguada commented Feb 4, 2014

I was talking with Forrest, and he plans to work on that in a week or two.

I found this examples about convolutions
http://www.evl.uic.edu/sjames/cs525/final.html

@zimenglan-sysu
Copy link

@Yangqing how to convert the 2 dimension convolution to 3 dimension convolution in the im2col.cpp and conv_layer.cpp files? Thinks

happynear pushed a commit to happynear/caffe that referenced this issue May 12, 2016
Merge caffe/windows@{2016-03-08} into master
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

4 participants