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 ComputationGraph error: "cannot do forward pass: inputs not set"

I'm trying to pass multiple inputs to a ComputationGraph, but keep getting the error "cannot do forward pass: inputs not set". What is my mistake here? ArrayList inAndOutNames = new ArrayList<>(); String[] inputNames = new…
Fi0x
  • 3
  • 2
0
votes
1 answer

Failed to allocate [xxx] bytes from HOST memory

After fixing Error loading ND4J Compressors (thank you Adam!), I get the following error: java.lang.RuntimeException: Failed to allocate 4735031021 bytes from HOST memory (or java.lang.RuntimeException: cudaMalloc failed; Bytes: [4735031021]; Error…
apollox
  • 101
  • 7
0
votes
1 answer

ERROR org.nd4j.linalg.compression.BasicNDArrayCompressor - Error loading ND4J Compressors via service loader

Trying to run DL4J using NVIDIA cuDNN library (Windows10): https://deeplearning4j.konduit.ai/multi-project/explanation/configuration/backends/cudnn In my pom I added: 16
apollox
  • 101
  • 7
0
votes
1 answer

ModelSerializer.writeModel and saveUpdater param

According to the description from the link: https://github.com/deeplearning4j/deeplearning4j-examples/blob/master/dl4j-examples/src/main/java/org/deeplearning4j/examples/quickstart/features/modelsavingloading/SaveLoadMultiLayerNetwork.java boolean…
apollox
  • 101
  • 7
0
votes
1 answer

DeepLearning4j - occurrences cannot be negative

I'm new to dL4J and keep running across this issue; java.lang.IllegalArgumentException: occurrences cannot be negative: -11668 And I really can't seem to workout why. I've checked my testData labels and the model output and there are definitely no…
Rus Kuzmin
  • 15
  • 4
0
votes
0 answers

Using DL4J in web application - RuntimeException: Op [matmul] execution failed

I have a MultiLayerNetwork which is loaded in an application which is loaded on a payara server. The model loads fine but on requesting an output on a INDArray I receive a RuntimeException. The system I'm working on seems to work fine during the…
0
votes
1 answer

LSTM in DL4J - All output values are the same

I'm trying to create a simple LSTM using DeepLearning4J, with 2 input features and a timeseries length of 1. I'm having a strange issue however; after training the network, inputting test data yields the same, arbitrary result regardless of the…
0
votes
1 answer

DL4J LSTM - Contradictory Errors

I'm trying to create a simple LSTM using Deeplearning4J in Java, with 2 input features and a timeseries length of 1. However, I'm running into an error concerning the number of input dimensions when calling predict(). import…
0
votes
1 answer

How to predict a float value using Deeplearning4J?

I have a dataset made up of around 50 csv files that each contain 2000-ish lines of 101 float values. The last value, the 101st, is the final value and the first 100 are a set of values that lead up to the final value. I would like to create a dl4j…
MBU
  • 401
  • 5
  • 16
0
votes
1 answer

Load ImageNet Data via Spark for AlexNet

I am working on the classification of Imagenet DataSet on AlexNet architecture. I am working on distributed systems for data streams. I am using DeepLearning4j library. I have a problem with loading Imagenet data from a path on our HPC. So my…
0
votes
2 answers

Cannot resolve symbol 'linspace' in ND4j

I'm pretty new in Java. I would like to initiate an array using Nd4j library INDArray x = new Nd4j.linspace(0, 1, 100);, doing something like x = np.linspace(0, 1, 100) in Python. And I ran into an error java: cannot find symbol symbol: class…
Zézouille
  • 503
  • 6
  • 21
0
votes
0 answers

Ho to compile deeplearning4j pretrained models into java bytecodes?

Why ask: I have trained a multi-layer network to recognize some specific soundwaves. It worked perfectly well, and costed only ~1ms to work. However, when I tried to migrate it to Android, I found to my astonishment that the apk is over 1GB. I…
0
votes
1 answer

java.net.ConnectException: Connection refused (Connection refused) in deepLearning4j

I am working on Deeplearning4j models on Spark. I want to enable Deeplearning4j-UI to follow up some graphs (training/testing..). I search about it and in some links they said that I should install the dependency maven-shade-plugin and the…
0
votes
1 answer

MultiLayerConfigureation returns DL4JInvalidInputException: Input size

My CSVDataset is structured as N,P,K,temperature,humidity,ph,rainfall,label 90,42,43,20.87974371,82.00274423,6.502985292000001,202.9355362,rice The goal is to predict the recommend the optimal crop given the features. My pipeline is as…
0
votes
1 answer

The XOR neural network written in DL4J does not work

I'm starting to study the neural network together with the DL4j framework and start with XOR training. But no matter what I do, I get the wrong results. MultiLayerConfiguration networkConfiguration = new NeuralNetConfiguration.Builder() …
Amos
  • 123
  • 1
  • 4