Comments (10)
I've run a lot of benchmarks that have shown that (1) peephole optimizations don't help (and usually hurt), and (2) any other choice of non-linearity other than the default one performs considerably worse.
I'll publish that as an Arxiv tech report soon.
from clstm.
Is the arxiv link of your tech report available now?
from clstm.
I got publication clearance, but it's not quite out yet. I'll try to push it in the next few days.
from clstm.
Thank you! Have you ever try to push a GPU version of LSTM since the community seems to have more interests in the RNN field?
from clstm.
I'm planning on GPU support via Eigen; however, that will still be a few months before the necessary dependencies are out.
from clstm.
@BestSonny, here it is:
Benchmarking of LSTM Networks
Thomas M. Breuel
http://arxiv.org/abs/1508.02774
from clstm.
Thank you!
from clstm.
@tmbdev , mshadow may be a strong alternative to Eigen. Both cxxnet and mxnet are built upon it.
from clstm.
Thanks. Looks like Eigen and mshadow have similar goals. Is there any performance data comparing the two?
from clstm.
@tmbdev , mshadow has very detailed tutorials and other documentations including multi-GPU support while Eigen documents almost nothing related to GPU on its official website.
More importantly, mshadow exploits the powerful NVIDIA cuDNN library. It's impossible for Eigen to catch up mshadow in performance on GPUs.
from clstm.
Related Issues (20)
- core dumped, w != 0 failed
- Missing last char of the line. HOT 4
- Sort and Sed commands are causing the model not to train (ERROR 1/OUT is empty) HOT 2
- Arabic 800,000 model cant go below Error Rate 0.5 HOT 4
- Always missing one character in the output HOT 3
- Can I use this tool to do scene text detection + recognition ? HOT 2
- Is it possible to train multiple languages on a one model file ? HOT 6
- Error in training uw3-500
- clstmocr - error opening clstm file (trained model) HOT 8
- Segmentation fault when running clstmocr on pre-trained model HOT 1
- Error while using clstm models that I trained and test it !
- I want to use gpu to speed up training model! How do I do, I follow the previous issu to do but failed
- error: use of undeclared identifier 'environ' HOT 6
- How to optimally prepare the data
- Segmentation Fault when running tests HOT 1
- Inaccurate training
- question: clstmocrtrain on GPU
- How to make predictions using python code
- Is there a graphical depiction of the model being used/trained here? HOT 4
- question HOT 2
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 clstm.