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:

413 questions
2
votes
1 answer

Train recurrent neural net in deeplearning4j with data that is generated during runtime

I'm new to the deeplearning4j library, but I've got some experience with neural networks in general. I'm trying to train a recurrent neural network (a LSTM in particular) which is supposed to detect beats in music in realtime. All examples for using…
2
votes
4 answers

Word2Vec with chinese

I have been learning about Word2Vec(Deeplearning4j) but i could find not anything about it supporting Chinese. From various sources I got to know that it can work for chinese also by using some plugin. So please tell me any plugin for chinese, also…
tushar garg
  • 69
  • 1
  • 6
2
votes
1 answer

Problems with loading nlp model with deeplearning4j

so I'm trying to implement the free deeplearning library for Java called deeplearning4j to tackle a classification task in nlp. public static void Learn(String labelledDataFileName) throws Exception { ParagraphVectors paragraphVectors = new…
2
votes
1 answer

deeplearning4j: online Word2Vec training

Word2vec is a great tool is deeplearning4j. I managed to create a vector for a corpus following this tutorial. The question now is how to update the model with new sentences without having to rebuild it again from scratch. Some thoughts on this,…
Mohamed Taher Alrefaie
  • 15,698
  • 9
  • 48
  • 66
1
vote
2 answers

Deeplearning4J Java code to predict price of Bitcoin is giving strange values

I put together some code that given an array containing the full time series of the daily Bitcoin close price in dollars, should produce a prediction for the price of Tomorrow. I would expect the result not to be too dissimilar from the current…
user1883212
  • 7,539
  • 11
  • 46
  • 82
1
vote
0 answers

How to code a RNN model using LSTM from deeplearning4j (DL4J) for regression to predict speed of a vehicle?

I'm new to DL4J and I need to code a RNN with LSTM to predict the future value of the speed of a moving vehicle. I have only one input which is the the time index and one output which is the speed. I've been researching for a while now on this, but…
NX20
  • 11
  • 1
1
vote
0 answers

Why is there shape error from imported Keras model in DL4J

I trained a model in Keras, this is my python code: model = Sequential() model.add(Embedding(50000, 128, input_length=10)) model.add(Conv1D(48, 5, activation='relu',…
HayWhy
  • 11
  • 2
1
vote
1 answer

Avoid platform specific dependencies in SBT packageBin

In a Java11 project (actually Java Play-Framework) I depend directly on org.deeplearning4j:deeplearning4j-nlp:1.0.0-M2 in my build.sbt running SBT 1.5.5. That dependency transitively depends on several other libraries (like e.g.…
jdo
  • 71
  • 5
1
vote
1 answer

Reduce DeepLearning4j dependency size of exported jar

In my application, I would like to use Deeplearning4j. Deeplearning4j has over 120mb of dependencies, which is a lot considering my own code is only 0.5mb. Is it possible to reduce the dependencies required? Would loading an already-trained network…
Joehot200
  • 1,070
  • 15
  • 44
1
vote
1 answer

Ask About The "default" Size of Vocabulary in Word2Vec in Deeplearning4j Library

I am currently learning about this library: Word2Vec from Deeplearning4j (Homepage, Github) Following is the example usage of the method: //build Word2Vec model Word2Vec vec = new Word2Vec.Builder() .layerSize(100) …
Sfaiz
  • 13
  • 3
1
vote
1 answer

Create efficiently `DataSetIterator` out of large double[][] array

I have large (1M samples * 100 features) array of type double[][] loaded into memory and I need to create efficiently DataSetIterator (with random batches) to feed MultiLayerNetwork. How can I do that? Most of the deeplearning4j examples I found…
kolar
  • 1,010
  • 1
  • 9
  • 21
1
vote
1 answer

Visualizing training progresss in deeplearning4j throws error when starting server

I was following this tutorial trying to visualize my models training progress: https://deeplearning4j.konduit.ai/tuning-and-training/visualization The simple code for the server setup is: UIServer uiServer = UIServer.getInstance(); StatsStorage…
David
  • 127
  • 5
1
vote
0 answers

TensorFlow Keras model cannot be loaded into Deeplearning4J due to custom layer

I have trained a TensorFlow Keras model in Python and saved it as trained_model.h5: model = tf.keras.Sequential([hub.KerasLayer("https://tfhub.dev/google/tf2-preview/mobilenet_v2/feature_vector/4", …
RazorAlliance192
  • 722
  • 9
  • 23
1
vote
1 answer

DeepLearning4J Problems with INDArray

public void playFullGame(MultiLayerNetwork m1, MultiLayerNetwork m2) { boolean player = false; while (!this.isOver) { float[] f = Main.rowsToInput(this.rows); System.out.println(f.length);// prints 42 INDArray…
David
  • 127
  • 5