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
1
vote
0 answers

Why a Graves-LSTM Cell has 4 + 7 = 11 weigths in deeplearning4j?

Why a Graves-LSTM layer Cell has 11 weigths, and what is their purpose? Given below example can generate weigth list: MultiLayerNetwork model = new MultiLayerNetwork(new NeuralNetConfiguration.Builder() .list() .layer(0, new…
Daniel Hári
  • 7,254
  • 5
  • 39
  • 54
1
vote
2 answers

Deeplearning4j: LSTM example for review sentiment analysis

I am looking through the example of deeplearning 4j for classifying movie reviews according to their sentiment. ReviewExample At line 124-142 the N-dimensional arrays are created and I am kind of unsure what is happening at these lines: Line 132:…
toobee
  • 2,592
  • 4
  • 26
  • 35
1
vote
0 answers

digits predict prob for test database

I am using digits for image classification task. I wanted to score the test db and get the predicted prob in csv file. Can anyone tell me where should i make changes in the digits files for that?
nitesh kansal
  • 131
  • 1
  • 4
1
vote
1 answer

Ant build.xml with Deeplearning4j and Lux Delux

I'm trying to create an AI for the risk game Lux Delux that will make use of a neural net trained in Deeplearning4j. Naturally, when I compile I get a bunch of package does not exist errors. How would one go about adding such dependencies to an ant…
Eric Gorlin
  • 319
  • 1
  • 8
1
vote
1 answer

Deeplearning4j LSTM Example

I am trying to understand LSTM on Deeplearning4j. I am examining source code for the example, but I can't understand this. //Allocate space: //Note the order here: // dimension 0 = number of examples in minibatch // dimension 1 =…
Nueral
  • 21
  • 2
1
vote
2 answers

Deeplearning4j to spark pipeline: Convert a String type to org.apache.spark.mllib.linalg.VectorUDT

I have a sentiment analysis program to predict whether a given movie review is positive or negative using recurrent neutral network. I'm using Deeplearning4j deep learning library for that program. Now I need to add that program to apache spark…
1
vote
1 answer

dl4j canova example not working

Deeplearning4j canova example not working.I am getting the output of eval.stats as NaN (accuracy).I import org.slf4j.LoggerFactory; public class ImageClassifierExample { public static void main(String[] args) throws IOException,…
Jishnu Prathap
  • 1,955
  • 2
  • 21
  • 37
1
vote
1 answer

Need some help for deeplearning4j single RBM usage

I have a bunch of sensors and I really just want to reconstruct the input. So what I want is this: after I have trained my model I will pass in my feature matrix get the reconstructed feature matrix back I want to investigate which sensor values…
KIC
  • 5,887
  • 7
  • 58
  • 98
0
votes
2 answers

Deeplearning4J RNN Training : Exception 3D input expected to RNN layer expected, got 2

with the following code (tweaked for hours with different params), I keep getting an exception java.lang.IllegalStateException: 3D input expected to RNN layer expected, got 2 What I am trying to accomplish is to train a RNN to predict the next value…
0
votes
1 answer

Deeplearning4J's SameDiff in Scala: INDArrays to DataSetIterator as input to sameDiff.fit

I went thru the basic linear regression example in the documentation using SameDiff which works fine in Scala 3.2. I then tried to train the linear regression with input and label INDArrays and that's where I get stuck. I can't find a way to convert…
0
votes
0 answers

Deeplearning4j Invoice extraction

Does anyone try to use Deeplearning4j to extract data from invoice? The idea is to train model, then send extracted text of incvoice as an input and receive predicted fields like invoice number, invoice date, customer name, etc. Any help is…
0
votes
1 answer

Problems converting deepLearning4j array to ONNX Tensor

I'm currently reading an image with deepLearning4j and trying to pass it to ONNX is giving me problems. INDArray ndArray = loader.asMatrix(mat3).permute(0,2,3,1); OnnxTensor tensor = OnnxTensor.createTensor(env, ndArray.data().asNioFloat(),…
IgnacioPL
  • 67
  • 1
  • 6
0
votes
3 answers

Java NLP - Insight from Text Data

We would like to do a POC that uses Java based NLP libraries like Stanford Core NLP and/or Deeplearning4J to train/use models that can extract insight / meaning / summary and provide answers to user queries against a custom document repository / DB…
Sabari
  • 127
  • 1
  • 13
0
votes
0 answers

how to resolve the ValueError: Unable to create dataset (name already exists)

I already have two pretrained keras models which I have uploaded in my drive and mounted it in colab. then I have given the model paths to load the models and then I tried to do ensembling: This is the code for model ensembling : model1 =…
0
votes
1 answer

How to update the weights in my q-network (deeplearning4j)

I want to create a deep q network with deeplearning4j, but can not figure out how to update the weights of my neural network using the calculated loss. (i was mainly following this Artical) public class DDQN { private static final double…