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:

413 questions
3
votes
2 answers

Convert keras model in DL4J model

I have to save and load a keras model in java and then I thought I could use DL4J. The problem is that when I save my model it does not have the Embedding layer with his own weight. I have the same problem re-loading the model in keras but in this…
AM13
  • 661
  • 1
  • 8
  • 18
3
votes
1 answer

How do i store and load trained data in deeplearning4j?

deeplearning4j : How can I store/save a trained model on persistence level and load it back when an ad-hoc request comes to evaluate the deep learning model? DataNormalization normalizer = new NormalizerStandardize(); …
Nabraj Khatri
  • 31
  • 2
3
votes
1 answer

Paragraph Vector or Doc2vec model size

I am using deeplearning4j java library to build paragraph vector model (doc2vec) of dimension 100. I am using a text file. It has around 17 million lines, and size of the file is 330 MB. I can train the model and calculate paragraph vector which…
tired and bored dev
  • 655
  • 10
  • 30
3
votes
1 answer

Is there a way to change a neural network's topology in DL4J without having to retrain it?

I need to make changes to an existing deeplearning4j (DL4J) model that has already been trained. The network consists of an input layer, one Graves LSTM and one RNN Output Layer. My question is: Is it possible to add one or more untrained neurons…
Edy Bourne
  • 5,679
  • 13
  • 53
  • 101
3
votes
1 answer

Data Type not understood in tensorflow

mean , variance = tf.nn.moments(X_train, axes = 1, keep_dims = True) I am trying to get the mean and variance using tf.nn.moments() as shown above. However, I am encountering the following…
Abhinandan
  • 33
  • 1
  • 4
3
votes
1 answer

DL4J Prediction Formatting

I have two questions on deeplearning4j that are somewhat related. When I execute “INDArray predicted = model.output(features,false);” to generate a prediction, I get the label predicted by the model; it is either 0 or 1. I tried to search for a way…
me._
  • 51
  • 1
  • 8
3
votes
2 answers

Running a neural network backwards with partial inputs to find desired values

Given a trained system, a network can be run backward with output values and partial inputs to find the value of a missing input value. Is there a name for this operation? In example with a trained XOR network with 2 input neurons (with values 1…
Beryllium
  • 556
  • 1
  • 7
  • 20
3
votes
1 answer

How to install the library Deeplearning4j with IntelliJ and Maven?

I'm trying to install the Deeplearning4j library ( https://deeplearning4j.org/index.html) but I don't understand how to use install the lib correctly with IntelliJ and Maven so that I can build a .jar file from it. As long as I'm running the…
Bohne
  • 173
  • 1
  • 7
  • 12
3
votes
1 answer

TransformProcess transform data while using DataSetIterator

I have a CSV dataset with both numerical and nominal attributes. I defined Schema for dataset that list all possible values for nominal attributes. After that I created TransformProcess to convert nominal values to numeric values using …
serdar
  • 974
  • 2
  • 16
  • 24
3
votes
1 answer

Run deeplearning4j without GPU?

The documentation says the library runs on GPUs. If my powerful laptop doesn't have a GPU, can I still run Deeplearning4J?
user697911
  • 10,043
  • 25
  • 95
  • 169
3
votes
1 answer

Integrate deeplearning4j with JHipster Maven pom.xml, getting SLF4J binding error

I tried to integrate deeplearning4j with JHipster pom.xml with the following: org.deeplearning4j deeplearning4j-core 0.8.0 …
William Cao
  • 71
  • 1
  • 3
3
votes
1 answer

Install DL4J on Windows

I have just followed the steps given on: https://deeplearning4j.konduit.ai/getting-started/quickstart (cloning it from github, executing mvn clean install, import the project into IntelliJ) and I was able to run the examples in IntelliJ. However, I…
Peter
  • 43
  • 5
3
votes
1 answer

What parts an parameters of train_val.prototxt, solver.prototxt, and deploy.prototxt should be changed based on our own data?

I am confused about changing the parameters for training a net in caffe based on our own data. Which layers of net we should pay attention more to train the net on our own data? For example, the number of outputs based on the number of classes. I…
S.EB
  • 1,966
  • 4
  • 29
  • 54
3
votes
3 answers

How to train a RBM and reconstruct input with DeepLearning4J?

I'm trying to train a Restricted Boltzmann Machine (RBM) with DeepLearning4J 0.7 but without success. All the examples I found are either not doing anything useful or not working anymore with DeepLearning4J 0.7. I need to train a single RBM with…
Baptiste Wicht
  • 7,472
  • 7
  • 45
  • 110
3
votes
2 answers

How to use a network for prediction in Deep Learning 4 j?

As a beginner in deep learning I am currently practicing using the project called deep learning 4 j. I am getting really good at the "training" and "evaluating" part of deep learning, but how am I supposed to deploy my finished network in an…
Mr. Developerdude
  • 9,118
  • 10
  • 57
  • 95
1 2
3
…
27 28