Comments (7)
about above comment:
its resolved - the script is updated :)
from clnn.
You'd probably best provide a complete script, so I can just copy and paste. But anyway, seems your Sequential needs running :cl()
against it, to convert it to cl
form?
from clnn.
Thanks Hugh. In fact, I figured out what was wrong.
I had this line
dtype = torch.Tensor():cl():type()
to get the cl() datatype, and then was executing
model = nn.Sequential():type(dtype)
but before defining the rest of the model, and not after!
from clnn.
I have another question though, can you please comment?
From everything I can see (Soumith's benchmarks, your discussion with PavelMiha in another issue, and my own experiments today), training on clnn seems to be no better than just doing it on nn. For example, a forward + backward pass in PavelMiha's network is 3x slower on clnn, and now I'm trying Szagoruyko's vgg+bn, which seems again ~2x slower.
I'm on Mac OS X with OpenCL device: ATI Radeon HD 6770M. I have 16 GB RAM and a 2.4Ghz Intel Core i7 CPU. Does my CPU have much better specs than my GPU, or is there really no benefit from running on clnn? I have tried different batch sizes (from 2 to 128 ... 512), but no parallelisation seems to happen.
I would really appreciate your thoughts. Thanks.
from clnn.
Well... an i7 is a good cpu. But yeah, on your hardware, it looks like you might as well train on cpu, rather than using gpu.
On my own laptop, gpu is quite a lot faster than my cpu, but generally speaking, I wouldnt actually train on my laptop as such: I'd just code on my laptop, and then transfer to some faster machine for the actual training task.
from clnn.
Hi,
I am just a newbie to LUA/Torch and was trying to execute : recurrent-visual-attention.lua. However, I am getting the same above error. can you help me if I find any fix ?
from clnn.
Awesome!
from clnn.
Related Issues (20)
- MSECriterion batch size limitation HOT 6
- "Abs.lua:8: attempt to index field 'THNN' (a nil value)" HOT 23
- mac build fails with "ld: library not found for -lTHC" HOT 5
- On Mac: "THCLNN.lua:11: bad argument #1 to 'load'" HOT 9
- Issue with using an older card or something in pre-reqs? HOT 63
- CLNN master/thnn4 build error HOT 18
- [FeatureRequest] port SpatialUpSamplingNearest and SpatialBatchNormalization from cunn HOT 35
- LookupTable broken HOT 3
- 4 error and 1 warning when run luajit -l clnn -e 'clnn.test()' HOT 4
- bad argument #1 to 'set' (expecting number or torch.FloatTensor or torch.FloatStorage) HOT 2
- temporal convolutions/pooling HOT 8
- SpatialConvolutionMM gives incorrect output with nOutputPlane == 7 HOT 3
- clnn for neuralconvo support. LogSoftMax.lua:23 HOT 15
- torch/install/share/lua/5.1/nn/THNN.lua:109: bad argument #8 to 'v' (cannot convert 'number' to 'struct THClTensor *') HOT 2
- "getting latest SpatialAveragePooling" instruction still present in README.md HOT 3
- Porting Convolutions and im2col HOT 17
- SpatialFullConvolution in clnn HOT 1
- warning: unused function 'IndexToOffset_999_get' HOT 5
- ERROR:PFUI.lua:8: attempt to index field 'gui' (a nil value)
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 clnn.