Questions tagged [dl4j]

Deeplearning4j is the first commercial-grade, open-source, distributed deep-learning library written for Java and Scala

About

Deeplearning4j is the first 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.

Links

208 questions
0
votes
1 answer

DL4J UI: How to display cost error of the validation test?

I use DL4J and I attach the UI. How can I display on UI the cost error of the validation set? What have I to configure? I have to check if there is overfitting but the UI display only the cost error of the training set. See the image attached…
Simona R.
  • 558
  • 6
  • 20
0
votes
1 answer

What reason could be for the F1 score that was not a harmonic mean of precision and recall

[![enter image description here][1]][1]What reason could be for the F1 score that was not a harmonic mean of precision and recall with macro-average weighted equally for multi-class? My dataset is imbalanced, and the predictions are skewed.
Java questioner
  • 157
  • 1
  • 4
  • 12
0
votes
1 answer

DeepLearning4j throwing "Intel MKL FATAL ERROR: Cannot load mkl_intel_thread.dll." error

Recently i started to learn DeepLearning4j library , so i cloned a dl4j project and executed in eclipse. After executing , it showed following error: Intel MKL FATAL ERROR: Cannot load mkl_intel_thread.dll. I checked my windows path variables and i…
Joby Wilson Mathews
  • 10,528
  • 6
  • 54
  • 53
0
votes
1 answer

Loading DL4J trained Word2Vec Model into gensim

Hello I have some word2vec models generated using Word2Vec java implementation in DL4J and saved by calling writeWord2VecModel(Word2Vec vectors, String path) The output of that is a zip file that contains a bunch of txt files. I can successfully…
Y2theZ
  • 10,162
  • 38
  • 131
  • 200
0
votes
1 answer

org.nd4j.linalg.factory.Nd4jBackend$NoAvailableBackendException in wildfly

I am using deeplearning4j with JBOSS wildfly. I have placed all the modules as mentioned below in the classpath:
Dwai
  • 119
  • 1
  • 15
0
votes
1 answer

Converting Dataframe from Spark to the type used by DL4j

Is there any convenient way to convert Dataframe from Spark to the type used by DL4j? Currently using Daraframe in algorithms with DL4j I get an error: "type mismatch, expected: RDD[DataSet], actual: Dataset[Row]".
atos
  • 37
  • 4
0
votes
1 answer

Putting a ComputationGraph in the resources directory in a JAR DL4j

Under normal circumstances, I can save a ComputationGraph (a Convolutional Neural Network) to a file and load it in a later run and it works fine. However, when I include it in a jar and I try to load it, it fails. Is there some way to load…
0
votes
1 answer

DL4J - When using a ComputationGraph, is it possible to get the Class labels from it?

I saw how to do this from a DataSet object, and I saw a setLabel method, and I saw a getLabelMaskArrays, but none of these are what I'm looking for. Am I just blind or is there not a way? Thanks
0
votes
1 answer

Parsing modified MNIST in the form of CSV for Conv Neural Network

I'm planning on using this modified version of MNIST for benchmarking research, but they are currently in .mat format. So, I've read on StackOverflow that MatlabRecordReader actually isn't that robust, and that it's far smarter to change the data…
Andy
  • 357
  • 2
  • 17
0
votes
1 answer

Semantic Segmentation using dl4j with FCN Networks

I have checked out dl4j examples and executed AnimalsClassification example for testing successfully. I have to train, evaluate and predict(use) a semantic segmentation algorithm like UNet, because input images are not the same size FCN is…
0
votes
1 answer

DL4J/ND4J: Can INDArray instance be reused?

I have a model to train on a large data set that does not fit into RAM. So, basically my plan is to slice the data set creating a DataSet instance with input vectors and associated labels for every chunk. E.g. if I have 1M input vectors/labels I'd…
faraway
  • 428
  • 2
  • 4
  • 15
0
votes
2 answers

Error loading own data set. numClasses and InputSplit

Unexpected exception when load own dataset. The execution of the code from FeaturizedPreSave with just a minor change in the number of samples to be taken into consideration for the neural network produce an exception of Unsupported…
Piastres
  • 1
  • 3
0
votes
1 answer

How do I remove dummy variable trap with OneHotencoding

Here is my code for CSV data extraction and transformation: Schema schema = new Schema.Builder() .addColumnsString("RowNumber") .addColumnInteger("CustomerId") .addColumnString("Surname") …
Rahul Raj
  • 3,197
  • 5
  • 35
  • 55
0
votes
1 answer

Solving DL4J compilation error

I am trying to download DL4J source without error. https://github.com/deeplearning4j/deeplearning4j I cloned https://github.com/deeplearning4j/deeplearning4j.git and imported using existing Maven project in Eclipse. Tons of dependencies are…
Calia Kim
  • 65
  • 14
0
votes
1 answer

DL4J: set "channels_first" config

I'm trying to load a pretrained Keras model into Java app using DL4J. When training in Keras I used "channels_first" image_data_format, and now, in DL4J I can not load my model properly, because it tries to use "channels_last" configuration. Is…
Bagoly Sz.
  • 156
  • 7