Comments (3)
ivan-vasilev
commented on August 29, 2024
Sorry for the late response. Judging by the log data it's possible that you don't have the mnist data files. You can download and extract them from this page (the first four links). The files have to be extracted under the nn-samples/ folder. I hope that helps
from neuralnetworks.
roideuniverse
commented on August 29, 2024
Hi Ivan,
Nice work here.
I just tried running MnistTest.java. I wonder why but and I am getting approximately 90% error. Is this expected observation?
TESTING testRBM...
2.7 s total time
0.27 s per minibatch of 10 mini batches
9146/10000 samples (0.9146, 91.46%) error
TESTING testLeNetSmall...
33.828 s total time
3.3828 s per minibatch of 10 mini batches
9020/10000 samples (0.902, 90.200005%) error
TESTING testLeNetTiny2...
3.174 s total time
3.173E-4 s per minibatch of 10000 mini batches
488/10000 samples (0.0488, 4.88%) error
TESTING testAE...
1.06 s total time
0.106 s per minibatch of 10 mini batches
8626/10000 samples (0.8626, 86.26%) error
TESTING testSigmoidBP...
1.076 s total time
0.1076 s per minibatch of 10 mini batches
898/10000 samples (0.0898, 8.98%) error
from neuralnetworks.
ivan-vasilev
commented on August 29, 2024
This should be fixed in the latest sources.
from neuralnetworks.
Related Issues (20)
- Is it possible to implement sparse autoencoder with your lib? HOT 1
- Simple forward example? HOT 1
- Test case MnistTest fail on every tests HOT 2
- Index out of range: 0 -> 89+0 to 0
- Differences between Java1.7 and Java1.8 neyral net libraries
- MnistTest.testLeNetSmall fails with 90% error rate HOT 1
- Could you please let me know if only changing the following line is enough to run the code in GPU. Environment.getInstance().setExecutionMode(EXECUTION_MODE.SEQ); to Environment.getInstance().setExecutionMode(EXECUTION_MODE.GPU); HOT 4
- XOR test fails
- Train method fails in MultipleNeuronsOutputError.getTotalErrorSamples
- Saving/Loading networks
- DBN with softmaxlayer on top
- How to run the project in Eclipse ?
- Can the examples run without opencl.so ?
- neuralnetworks is 2000 times slower using GPU than Theano using CPU HOT 1
- How can I train my net with deep learning ?
- OS Differences
- Strange behavior when calculating Layers (probably Aparapi related) HOT 2
- Execution mode GPU failed: OpenCL execution seems to have failed (runKernelJNI returned -51) com.aparapi.internal.exception.AparapiException: OpenCL execution seems to have failed (runKernelJNI returned -51)
- OpenCl problem
- Is this repo dead ? HOT 3
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 neuralnetworks.