Comments (15)
What's your use case? Do you want it mt-safe for training or testing/prediction? Thanks!
from smile.
My case: I am looking for a NeuralNet capable to train a corpus of 20GB data in a 8-thread server. Already tried @deeplearning4j and other java impl., but didn't like any of it.
Predicting not mt-safe could be bypassed implementing a resource manager (such as priority queue or duplicating models).
Since Smile was clean, source independent and intuitive (got running mt-thread SVM and Random Forest in a couple minutes), thought to ask about project priorities :)
from smile.
I doubt how much we can gain by making training of neural net mt-safe. There are a lot of shared data (weights in the net). To make it mt-safe, locking/mutex will make it slow. Can you have a try with your data in single thread to see how long it takes? Thanks!
BTW, Neural Net of smile is traditional back propagation algorithm. It is different deep learning and is suitable for different problems.
from smile.
Wow, it makes sense. I will give a try and and im closing this issue. Thanks for the answer!
from smile.
Any updates? Is it too slow for you? Thanks!
from smile.
Found some bugs in my code at "processing features" phase. After validating this, I am going to test and post some results here!
from smile.
Thanks! If you have any questions about Smile's NeuralNetwork, please feel free open a ticket.
from smile.
Hi, finally got my first results.
Training 10k instances (14k attributes) got 33 seconds to learn.
Train size:10000
Training in: 33.127 seconds
Test size: 1000
Finishing Cross Validation
Final precision: 0.91607128289355
Final recall: 0.908765520895934
Next step: 100k
from smile.
Given the sample size, the number of attributes, this looks very good to you. How do you feel? Especially compared to your experience with other packages? Thank you very much for reporting the results!
Btw, what's neural net settings?
from smile.
Can you please write a post on our wiki describing what you are doing? It doesn't have to be long. Simply describe your data and your problem, why you choose neural net, how you train and test the model (and some code snippets). This will be extremely valuable for others. Thanks a lot in advance!
from smile.
BTW, our SVM training algorithm is also an online algorithm. You may want to give it a try and compare it to neural net. Thanks!
from smile.
My experience has been awesome. Please, keep this great job, elegant and effective :)
And sure, it would be great! I am going to test everything before and then I will write the post.
About SVM, I tried it in first time. But got results on 0.7 / 0.9 in prec/recall. And it got time to train (like 250 seconds). But I will give a second try, right after implement a naive grid search.
Thanks!
from smile.
How's going with 100k?
from smile.
Hi! Really sorry for the delay. I was "stormed" by my Master's thesis qualification (writing and evaluating a lot what already did).
Getting back to the track tomorrow and hope to give good news (results and blog post) soon.
from smile.
Thanks for updates! Hope everything is fine with you.
from smile.
Related Issues (20)
- stringVector(0) error HOT 1
- Suggest changing license to Apache 2.0 license or MIT
- Non-monotonic cluster tree -- the linkage is probably not appropriate! HOT 1
- HiddenLayerBuilder does not add dropout to HiddenLayer HOT 4
- Method in interface BaseArray can never return an int[] HOT 2
- Making the plot module available in Java API HOT 4
- InnerProduct of vectors created with cas.Vars not being simplified HOT 6
- Support header attribute on facet / row / column encoding channels HOT 2
- Incorrect spec generated for encoding channel sort HOT 4
- How can I set up in Intellij or other IDE to compile and read code? HOT 3
- What is the efficient way to fill null values in a column with an arbitrary string in a Dataframe? HOT 3
- ClassCastException when calling DataFrame.omitNullRows() HOT 1
- smile.plot.swing.BarPlot works with smile-plot 3.0.2 but not with 3.1.0 HOT 2
- IllegalArgumentException when suing SimpleImputer for data sourced from json file HOT 1
- Is there any possibility to use ID3 or C4.5 via the Smile Package in Java? HOT 1
- Issue: Error with Prediction Method in Random Forest and Gradient Boost Regression HOT 3
- F1, precision & recall for multi-class classification HOT 5
- Predict requires DataFrame that contains the predicted variable in 3.1.0 HOT 5
- Suspicious discontinuity in run time with LU decomposition HOT 2
- Hard Coded Max Limit In FP Tree HOT 1
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 smile.