Stack Overflow
Stack Overflow

Questions tagged [deeplearning4j]

Deeplearning4j is commercial-grade, open-source, distributed deep-learning library written for Java and Scala. Integrated with Hadoop and Spark, DL4J is designed to be used in business environments, rather than as a research tool.

Deeplearning4j is a deep learning programming library written for Java and the Java virtual machine (JVM) and a computing framework with wide support for deep learning algorithms (such as Boltzmann machine, deep belief net, deep autoencoder, stacked denoising autoencoder and recursive neural tensor network, word2vec, doc2vec, and GloVe).

These algorithms all include distributed parallel versions that integrate with Apache Hadoop and Apache Spark.

For more information: deeplearning4j site, source code, support forum

Related Tags:

379 questions
19
votes
3 answers

deeplearning4j - using an RNN/LSTM for audio signal processing

I'm trying to train a RNN for digital (audio) signal processing using deeplearning4j. The idea is to have 2 .wav files: one is an audio recording, the second is the same audio recording but processed (for example with a low-pass filter). The RNN's…
erikd71
  • 199
  • 5
18
votes
1 answer

Does Gensim library support GPU acceleration?

Using Word2vec and Doc2vec methods provided by Gensim, they have a distributed version which uses BLAS, ATLAS, etc to speedup (details here). However, is it supporting GPU mode? Is it possible to get GPU working if using Gensim?
Irene Li
  • 281
  • 1
  • 3
  • 6
11
votes
1 answer

RNTN implementation in java

I want to implement a Recursive neural tensor network(RNTN) in java. I've used Deeplearning4j for word2vec pipeline to vectorize a corpus of words. for NLP pipeline I've used Opennlp.( for tokenizing, POStaging and parsing) Now, I figured out that I…
iamgr007
  • 966
  • 1
  • 8
  • 27
11
votes
1 answer

org.nd4j.linalg.factory.Nd4jBackend$NoAvailableBackendException

I don't know what it wants from me. I am using org.deeplearning4j deeplearning4j-core ${deeplearning4j.version} …
Stefan Falk
  • 18,764
  • 34
  • 144
  • 286
9
votes
2 answers

Neural Network returning NaN as output

I am trying to write my first neural network to play the game connect four. Im using Java and deeplearning4j. I tried to implement a genetic algorithm, but when i train the network for a while, the outputs of the network jump to NaN and I am unable…
David
  • 127
  • 5
8
votes
2 answers

How can I use a custom data model with Deeplearning4j?

The base problem is trying to use a custom data model to create a DataSetIterator to be used in a deeplearning4j network. The data model I am trying to work with is a java class that holds a bunch of doubles, created from quotes on a specific stock,…
Ethan
  • 87
  • 1
  • 5
8
votes
1 answer

Deeplearning4j: Iterations, Epochs, and ScoreIterationListener

Good afternoon to everybody. I'm quite new to the Deepleaning4j library and there are a couple of stuff that are still unclear to me. The concept of "epoch" is not new, thus, it is clear that it represents a full-cycle on the training set. My first…
Mauro
  • 91
  • 4
8
votes
2 answers

DL4J is super slow on GoogleNews-vectors file

I tried to execute the following example on DL4J (loading pre-trained vectors file): File gModel = new File("./GoogleNews-vectors-negative300.bin.gz"); Word2Vec vec = WordVectorSerializer.loadGoogleModel(gModel, true); InputStreamReader r = new…
Eugene Retunsky
  • 12,451
  • 3
  • 46
  • 53
7
votes
4 answers

Which is best for object localization among R-CNN, fast R-CNN, faster R-CNN and YOLO

what is the difference between R-CNN, fast R-CNN, faster R-CNN and YOLO in terms of the following: (1) Precision on same image set (2) Given SAME IMAGE SIZE, the run time (3) Support for android porting Considering these three criteria which is the…
Santle Camilus
  • 777
  • 1
  • 11
  • 19
6
votes
1 answer

Is it possible to use gensim word2vec model in deeplearning4j.word2vec?

I'm new to deeplearning4j, i want to make sentence classifier using words vector as input for the classifier. I was using python before, where the vector model was generated using gensim, and i want to use that model for this new classifier. Is it…
zunzelf
  • 85
  • 1
  • 5
5
votes
1 answer

Rnn Neural Network predict return unexpected predictions

I am triying to configure an RNN neural netwwork in order to predict 5 different types of text entities. I am using the next configuration: MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder() .seed(seed) …
Martin
  • 1,115
  • 1
  • 12
  • 40
5
votes
1 answer

keras: extracting weights using get_weights function

I would like to extract weights of 1d CNN layer, and understand how exactly the prediction values are computed. I am not able to re-produce the prediction values using the weights from get_weights() function. In order to explain my understanding,…
FairyOnIce
  • 2,236
  • 5
  • 21
  • 46
5
votes
1 answer

Is there any example of using weighted loss for pixel-wise segmentation/classification tasks?

I am doing FCN32 semantic segmentation on my data. I ran the algorithm to fine-tune for my data (grayscale images with only one channel), till 80,000 iterations; however, the loss and accuracy are fluctuating and the output image completely black.…
S.EB
  • 1,596
  • 2
  • 16
  • 42
5
votes
0 answers

FatJar from sbt-assembly throw java.lang.NoClassDefFoundError

I'm trying to execute a fat jar builded with sbt-assembly using spark and deepLearning4J, unfortunately during execution i'm confronted to the Exception in thread "main" java.lang.NoClassDefFoundError: error for many jars. I tried to add jars using…
KyBe
  • 832
  • 1
  • 11
  • 28
5
votes
4 answers

How to setup scala sbt project for nd4j and deeplearning4j

I want to run the LSTM code from deeplearning4j examples in my own sbt project using scala. My setup is Ubuntu 14.04, sbt 0.13, Oracle Java 8, nd4j version 0.5.0, scala 2.11.8. My approach can be found in my git repo. Feel free to clone it. On…
Sebastian
  • 281
  • 1
  • 8
1
2 3
…
25 26