Comments (16)
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 :-)
from deepcl.
Oh, hmmm, kernels.... is this for Inception?
from deepcl.
Mainly for NLP and other sequence processing.
from deepcl.
Ah, hmmm, right.
Presumably you'd want the input 'images' to also be non-squared too? Presumably, quite very not-square, like 1-dimensional?
from deepcl.
Yeah,exactly.
from deepcl.
Hmmm... does sound potentially quite useful generally. By the way, just out of curiosity do you know any papers that use this technique?
from deepcl.
http://nal.co/papers/Kalchbrenner_DCNN_ACL14
http://nlp.stanford.edu/~socherr/EMNLP2013_RNTN.pdf
http://www-nlp.stanford.edu/pubs/SocherLinNgManning_ICML2011.pdf
from deepcl.
Thanks!
from deepcl.
+1. Has there been any progress with this?
from deepcl.
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:
- make it only for 1-d, ie not generally rectangular support
- use the existing im2col convolution implementation. It's fast, and means you wont need to roll up your sleeves and dive into opencl too much (might need to ... a bit... for im2col ... maybe :-P)
It is however non-trivial enough that I'm not just going to spend a few hours one morning, and make it work. It's probably about a weeks work, I would think, ballpark. 40-80 man-hours or so.
from deepcl.
Note: I think an appropriate way forward for this might be to migrate to use BVLC/caffe#4155 , so that any kernels are shared across OpenCL projects.
from deepcl.
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.
from deepcl.
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 [email protected] 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:
#37 (comment)
Sent from my Android device with K-9 Mail. Please excuse my brevity.
from deepcl.
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.
from 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.
from deepcl.
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 :)
from deepcl.
Related Issues (20)
- clBlas error HOT 5
- MNIST data format HOT 1
- Python Q-Learning - Add Dropout Layout causes runtime error HOT 11
- can passed all test in #ad1ab61, but not now (#b256220) HOT 48
- function "NetLearner::learn" is deprecated, how to train a network by the new method? HOT 2
- How to use ExpectedData correctly in training? HOT 2
- tutorial and documentation is very less
- integrated demo HOT 2
- could deepcl run on FPGAs? HOT 1
- deepcl_predict HOT 5
- does the Neural network created on GPU? HOT 3
- captcha
- pip with windows does not work
- Need cythonize
- deepcl_unittests not running in CentOS 7. HOT 2
- opencl 1.1?
- Feature Request: Add Mish activation HOT 3
- How to set stride of conv layer? HOT 2
- Implementation of DNN on FPGA HOT 2
- Any examples for face detection?
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from deepcl.