Open brazilla opened 8 years ago
Understood. Involves a fair amount of work. Will ponder. Anyone else who arrives in this thread, and wants non-square kernels, please add a +1
into this thread, to motivate me a bit :-)
Oh, hmmm, kernels.... is this for Inception?
Mainly for NLP and other sequence processing.
Ah, hmmm, right.
Presumably you'd want the input 'images' to also be non-squared too? Presumably, quite very not-square, like 1-dimensional?
Yeah,exactly.
Hmmm... does sound potentially quite useful generally. By the way, just out of curiosity do you know any papers that use this technique?
Thanks!
+1. Has there been any progress with this?
Hmmmm .... well.... clnn contains a wrapper for 1-d convolutions. https://github.com/hughperkins/clnn/blob/master/TemporalConvolution2.lua I confess I'm unlikely to dedicate any time to implementing this in DeepCL in the short-term. I dont imagine it's tons of work, as long as you:
Note: I think an appropriate way forward for this might be to migrate to use https://github.com/BVLC/caffe/issues/4155 , so that any kernels are shared across OpenCL projects.
hi,@hughperkins did DeepCL support 3D square convolutional layers ? e.g. 3x3x64, which means size of filter is width 3,height 3 and depth 64.
Correct. Can you confirm what makes you feel this might not be the case?
On 15 November 2016 10:35:01 GMT+00:00, dex1990 notifications@github.com wrote:
hi,@hughperkins did DeepCL support 3D square convolutional layers ? e.g. 3x3x64, which means size of filter is width 3,height 3 and depth 64.
You are receiving this because you were mentioned. Reply to this email directly or view it on GitHub: https://github.com/hughperkins/DeepCL/issues/37#issuecomment-260606541
Sent from my Android device with K-9 Mail. Please excuse my brevity.
Thank you for your answer. I have not found any example on it, maybe i missed some relevant examples. I have trained model from this project: https://github.com/huangzehao/caffe-vdsr some layers of this network have input size: 40x40x64 and 64 filters with size: 3x3x64, so the output size is 40x40x64. I want to test the trained network with DeepCL.
I'm interested in adding 3D convolutional filters (once I do some more reading), but I'm hoping to have a proposal for stride in the not too distant future.
I wonder how hard 1D would be after doing that.
I'm hoping to have a proposal for stride in the not too distant future.
Sounds good :)
I wonder how hard 1D would be after doing that.
Its not conceptually hard, but it might involve a certain amount of legwork :)
Currently only 2D square convolutional kernels are supported. Thx.