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
feature request: "a trou" (with hole algorithm) #1815
Comments
I believe this is a duplicate of #889, which contains a workaround. I'll close this one, but we still have to fix it. |
It's not a duplicate, atrous convolution is adding holes in the input patch, whereas #889 is about dense patches but large strides. |
Hello Martin, Thanks for the super quick reply. Let me know if you need additional details. On Thu, Apr 7, 2016 at 5:12 PM, Martin Wicke notifications@github.com
|
For future reference, this is supported in Caffe master branch now and it is one of the features in Caffe rc3 https://github.com/BVLC/caffe/releases/tag/rc3. It is called dilation in convolution parameter and added by pull request BVLC/caffe#3487. There was detailed discussion about whether this feature should be named dilation, hole or atrous in this pull request BVLC/caffe#3452. Relevant discussion started on Dec 18, 2015 in the pull request. This feature is eventually called dilation in convolution or dilated convolution following the term in Holschneider et al. (1987). The Caffe developers concluded that "dilated convolution" is a historically more accurate name than "à trous convolution". |
@gpapan I assigned you based on your email to @yaroslavvb. Thanks! |
Thanks. This will be ready in the next few days. |
The change is in the process of being committed to github's Tensorflow. |
Thank @gpapan for adding this to TensorFlow! |
You are very welcome @fyu! Hope that people find this feature useful. |
Hi, all the best
|
@laurentk67 |
Having atrous convolution in TensorFlow is great - thank you @gpapan. I'd like access to strides for learning multi-scale raw audio filters, where using a stride of 1 is computationally infeasible. |
You should file a new issue with that feature request, I doubt it will be seen hidden in this thread. |
…velop-upstream-roctracer-piptest follow-up tensorflow#1815 to fix SWDEV-352934
To generate dense feature maps (e.g. semantic segmentation) the convolution and the maxpooling operators should have the option to define "holes" in the kernel.
The concept is used in the paper:
Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
(Liang-Chieh Chen, George Papandreou, Iasonas Kokkinos, Kevin Murphy, Alan L. Yuille)
and it is implemented in the excellent deeplab library based on Caffe.
The text was updated successfully, but these errors were encountered: