-
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
Document and Test Convolution #1104
Conversation
2d27796
to
580fe67
Compare
|
* inputs so that the im2col matrix has a column for each input region to | ||
* be filtered. col2im restores the output spatial structure by rolling up | ||
* the output channel N' columns of the output matrix. | ||
* | ||
* TODO(dox): thorough documentation for Forward, Backward, and proto params. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
rm TODO, nice docs!
probably worth switching to random weights, but I'll leave it up to you. otherwise LGTM! |
580fe67
to
6da8ce3
Compare
6da8ce3
to
7625cc5
Compare
To thoroughly check convolution, the output is compared against a reference implementation by explicit looping. Simple and group convolution by the Caffe and cuDNN engines are checked against the reference.
7625cc5
to
18ca362
Compare
Switched to random weights and uncovered a grouping issue in my reference convolution, so yeah, it was worth it. Ready for merge once Travis oks it. |
Document and Test Convolution
Document and Test Convolution
Document and Test Convolution
To thoroughly check convolution, the output is compared against a reference implementation by explicit looping. Simple and group convolution by the Caffe and cuDNN engines are checked against the reference.
The reference convolution rolls 8 loops deep.