# Uncategorized

**URL:** https://community.konduit.ai/c/uncategorized/1.md

[Latest](https://community.konduit.ai/latest.md) · [Categories](https://community.konduit.ai/categories.md)

---

## [New release soon](https://community.konduit.ai/t/new-release-soon/3530)

<div class="topic-metadata">

**Author:** [@agibsonccc](https://community.konduit.ai/u/agibsonccc)\
**Replies:** 7\
**Last updated:** [July 10, 2026, 10:18pm UTC](https://community.konduit.ai/t/new-release-soon/3530 "2026-07-10T22:18:01Z")

</div>

Hello all: After a long time waiting the release will be coming out. You can get a preview of what to expect here with the links below: Some upcoming things to expect: Dl4j as it stands will NOT be what it was. The …

---

## [Can nd4j-onnxruntime use GPU for ONNX model inference?](https://community.konduit.ai/t/can-nd4j-onnxruntime-use-gpu-for-onnx-model-inference/3405)

<div class="topic-metadata">

**Author:** [@LiuJia](https://community.konduit.ai/u/LiuJia)\
**Replies:** 1\
**Last updated:** [October 14, 2025, 9:43am UTC](https://community.konduit.ai/t/can-nd4j-onnxruntime-use-gpu-for-onnx-model-inference/3405 "2025-10-14T09:43:18Z")

</div>

Can nd4j-onnxruntime use GPU for ONNX model inference? deeplearning4j-cuda-11.2 1.0.0-M1.1 nd4j-cuda-11.2 1.0.0-M1 nd4j-onnxruntime 1.0.0-M1.1 When I use this version of nd4j-onnxruntime for inference, the outp…

---

## [sun.misc.Unsafe and pom file](https://community.konduit.ai/t/sun-misc-unsafe-and-pom-file/3382)

<div class="topic-metadata">

**Author:** [@carlo8767](https://community.konduit.ai/u/carlo8767)\
**Replies:** 2\
**Last updated:** [July 31, 2025, 10:35am UTC](https://community.konduit.ai/t/sun-misc-unsafe-and-pom-file/3382 "2025-07-31T10:35:41Z")

</div>

Hello, I want to ask if there is any project that you are working for update the pom file with a java version more stable. I want to highlight how the use of native access exposes you project at possible memory leak a…

---

## [Where can I get the code for the deep reinforcement learning example implemented by DL4J?](https://community.konduit.ai/t/where-can-i-get-the-code-for-the-deep-reinforcement-learning-example-implemented-by-dl4j/3357)

<div class="topic-metadata">

**Author:** [@tenstepd](https://community.konduit.ai/u/tenstepd)\
**Replies:** 2\
**Last updated:** [May 7, 2025, 11:12am UTC](https://community.konduit.ai/t/where-can-i-get-the-code-for-the-deep-reinforcement-learning-example-implemented-by-dl4j/3357 "2025-05-07T11:12:18Z")

</div>

I can’t find it on the official website https://deeplearning4j.konduit.ai/

---

## [Where to Find DL4J Example Data](https://community.konduit.ai/t/where-to-find-dl4j-example-data/3339)

<div class="topic-metadata">

**Author:** [@mrenzi](https://community.konduit.ai/u/mrenzi)\
**Replies:** 1\
**Last updated:** [March 14, 2025, 1:36am UTC](https://community.konduit.ai/t/where-to-find-dl4j-example-data/3339 "2025-03-14T01:36:25Z")

</div>

Is the dl4j example data still available anywhere. I’m trying to run the BasicCSVClassifier but it is failing at: dataLocalPath = DownloaderUtility.DATAEXAMPLES.Download(); eats = readEnumCSV(“animals/eats.csv”); sou…

---

## [Help for "Sequence lengths do not match for RnnOutputLayer input and labels:Arrays should be rank 3 with shape \[minibatch, size, sequenceLength\] - mismatch on dimension 2 (sequence length) - input=\[32, 15, 20\] vs. label=\[32, 5, 20\]"](https://community.konduit.ai/t/help-for-sequence-lengths-do-not-match-for-rnnoutputlayer-input-and-labels-arrays-should-be-rank-3-with-shape-minibatch-size-sequencelength-mismatch-on-dimension-2-sequence-length-input-32-15-20-vs-label-32-5-20/3331)

<div class="topic-metadata">

**Author:** [@linmeihong](https://community.konduit.ai/u/linmeihong)\
**Replies:** 2\
**Last updated:** [February 23, 2025, 5:37pm UTC](https://community.konduit.ai/t/help-for-sequence-lengths-do-not-match-for-rnnoutputlayer-input-and-labels-arrays-should-be-rank-3-with-shape-minibatch-size-sequencelength-mismatch-on-dimension-2-sequence-length-input-32-15-20-vs-label-32-5-20/3331 "2025-02-23T17:37:49Z")

</div>

I implements an example using LSTM and ComputationGraph,but an exception throwed. my deeplearning4j version is 1.0.0-M2.1. can anyone help me? thank you very much. Exception in thread “main” java.lang.IllegalStateExcep…

---

## [Data Forecasting Model Sequence to Sequence](https://community.konduit.ai/t/data-forecasting-model-sequence-to-sequence/3326)

<div class="topic-metadata">

**Author:** [@otterslide](https://community.konduit.ai/u/otterslide)\
**Replies:** 0\
**Last updated:** [February 15, 2025, 3:39am UTC](https://community.konduit.ai/t/data-forecasting-model-sequence-to-sequence/3326 "2025-02-15T03:39:22Z")

</div>

Hello, Does anyone know where I can find a Sequence to Sequence example with multiple features, in which the input sequence has a different number of timesteps than the output sequence? For example feed 5 days of data,…

---

## [Logging of deeplearning4J](https://community.konduit.ai/t/logging-of-deeplearning4j/3324)

<div class="topic-metadata">

**Author:** [@galera](https://community.konduit.ai/u/galera)\
**Replies:** 1\
**Last updated:** [February 14, 2025, 11:39am UTC](https://community.konduit.ai/t/logging-of-deeplearning4j/3324 "2025-02-14T11:39:44Z")

</div>

I try to stop logging using deeplearningFor4J creating a logback.xml file: %d{yyyy-MM-dd HH:mm:ss} %-5level %logger{36} - %msg%n \<logger name="org.deeplearning4j.nn.multilayer.MultiLayerNetwork" level="INFO" a…

---

## [Exception in thread "main" java.lang.UnsatisfiedLinkError: no jnitensorflow in java.library.path: \[/usr/java/packages/lib, /usr/lib/x86\_64-linux-gnu/jni, /lib/x86\_64-linux-gnu, /usr/lib/x86\_64-linux-gnu, /usr/lib/jni, /lib, /usr/lib\]](https://community.konduit.ai/t/exception-in-thread-main-java-lang-unsatisfiedlinkerror-no-jnitensorflow-in-java-library-path-usr-java-packages-lib-usr-lib-x86-64-linux-gnu-jni-lib-x86-64-linux-gnu-usr-lib-x86-64-linux-gnu-usr-lib-jni-lib-usr-lib/3207)

<div class="topic-metadata">

**Author:** [@mar](https://community.konduit.ai/u/mar)\
**Replies:** 1\
**Last updated:** [August 12, 2024, 11:18am UTC](https://community.konduit.ai/t/exception-in-thread-main-java-lang-unsatisfiedlinkerror-no-jnitensorflow-in-java-library-path-usr-java-packages-lib-usr-lib-x86-64-linux-gnu-jni-lib-x86-64-linux-gnu-usr-lib-x86-64-linux-gnu-usr-lib-jni-lib-usr-lib/3207 "2024-08-12T11:18:03Z")

</div>

Error log: Debug: Loading class org.bytedeco.javacpp.presets.javacpp Debug: Loading class org.bytedeco.javacpp.Loader Debug: Loading library jnijavacpp Debug: Failed to load for jnijavacpp: java.lang.UnsatisfiedLinkErr…

---

## [Help with TinyYoloHouseNumberDetection example](https://community.konduit.ai/t/help-with-tinyyolohousenumberdetection-example/3173)

<div class="topic-metadata">

**Author:** [@Hekk4](https://community.konduit.ai/u/Hekk4)\
**Replies:** 2\
**Last updated:** [June 14, 2024, 3:59pm UTC](https://community.konduit.ai/t/help-with-tinyyolohousenumberdetection-example/3173 "2024-06-14T15:59:48Z")

</div>

Hello, I used the example from github TinyYoloHouseNumberDetection to train a model and then I used it with the test data to identify the numbers from houses and their location but didn’t get the expected result. This is…

---

## [Possibilities on generating embeddings from BERT models in DL4J](https://community.konduit.ai/t/possibilities-on-generating-embeddings-from-bert-models-in-dl4j/3167)

<div class="topic-metadata">

**Author:** [@ssharma](https://community.konduit.ai/u/ssharma)\
**Replies:** 1\
**Last updated:** [June 6, 2024, 8:08am UTC](https://community.konduit.ai/t/possibilities-on-generating-embeddings-from-bert-models-in-dl4j/3167 "2024-06-06T08:08:15Z")

</div>

Is it possible to generate embeddings in DL4J using SameDiff? Recently I created a frozen BERT from one of Hugging Face BERT models. I was able to load it successfully using the SameDiff but while running the inference I…

---

## [Jetson nano in 1.0.0-M2.1 or 1.0.0-beta7](https://community.konduit.ai/t/jetson-nano-in-1-0-0-m2-1-or-1-0-0-beta7/3155)

<div class="topic-metadata">

**Author:** [@Paul](https://community.konduit.ai/u/Paul)\
**Replies:** 1\
**Last updated:** [May 27, 2024, 12:49pm UTC](https://community.konduit.ai/t/jetson-nano-in-1-0-0-m2-1-or-1-0-0-beta7/3155 "2024-05-27T12:49:49Z")

</div>

In build dl4j-master.version: 1.0.0-beta7: org.nd4j: nd4j-cuda-10.0, org.bytedeco: cuda: 10.0-7.4-1.5, org.deeplearning4j: deeplearning4j-core (using ComputationGraph KerasModelImport.importKerasModelAndWeights with …

---

## [Package org.nd4j.autodiff.validation.listeners not found in module](https://community.konduit.ai/t/package-org-nd4j-autodiff-validation-listeners-not-found-in-module/3145)

<div class="topic-metadata">

**Author:** [@Migel077](https://community.konduit.ai/u/Migel077)\
**Replies:** 2\
**Last updated:** [May 15, 2024, 12:07pm UTC](https://community.konduit.ai/t/package-org-nd4j-autodiff-validation-listeners-not-found-in-module/3145 "2024-05-15T12:07:10Z")

</div>

Trying create javafx app with deepleaning4j. Got this error while trying to strat my app: Error occurred during initialization of boot layer java.lang.module.FindException: Error reading module: C:\\Users\\Migel.m2\\repo…

---

## [Decision Transformer](https://community.konduit.ai/t/decision-transformer/3119)

<div class="topic-metadata">

**Author:** [@kgoderis](https://community.konduit.ai/u/kgoderis)\
**Replies:** 7\
**Last updated:** [April 21, 2024, 11:04am UTC](https://community.konduit.ai/t/decision-transformer/3119 "2024-04-21T11:04:54Z")

</div>

I was wondering if anyone has already tried to build a decision transformer using DL4J? And, or, tried to extend GPT-2, for example, from a Hugging Face model

---

## [Am i safe with those vurnerable dependencies?](https://community.konduit.ai/t/am-i-safe-with-those-vurnerable-dependencies/3105)

<div class="topic-metadata">

**Author:** [@rebok](https://community.konduit.ai/u/rebok)\
**Replies:** 1\
**Last updated:** [March 23, 2024, 11:41pm UTC](https://community.konduit.ai/t/am-i-safe-with-those-vurnerable-dependencies/3105 "2024-03-23T23:41:31Z")

</div>

I installed DL4j-core and i got few warnings related to using vurnerable depenendecies: Am i safe, if not what should i do to protect myself?

---

## [CNN Input Shape](https://community.konduit.ai/t/cnn-input-shape/3090)

<div class="topic-metadata">

**Author:** [@bugzyUK](https://community.konduit.ai/u/bugzyUK)\
**Replies:** 3\
**Last updated:** [March 13, 2024, 10:24am UTC](https://community.konduit.ai/t/cnn-input-shape/3090 "2024-03-13T10:24:37Z")

</div>

I am having difficulty when it comes to loading a model, and then finding the required input shape for it. I can create, train and infer from a CNN model whenI know what the input shape is by using this line. imageNati…

---

## [python4j spring boot jar PythonExecutioner init error](https://community.konduit.ai/t/python4j-spring-boot-jar-pythonexecutioner-init-error/2950)

<div class="topic-metadata">

**Author:** [@aizhimin](https://community.konduit.ai/u/aizhimin)\
**Replies:** 3\
**Last updated:** [December 10, 2023, 6:05am UTC](https://community.konduit.ai/t/python4j-spring-boot-jar-pythonexecutioner-init-error/2950 "2023-12-10T06:05:35Z")

</div>

In spring boot application, I builded a jar with maven 3.9.5, and then run it: java -jar true-north.jar. PythonExecutioner.init got a error: java.lang.ExceptionInInitializerError: null at com.banji.truenorth.runner.Ap…

---

## [LSTMAutoEncoder](https://community.konduit.ai/t/lstmautoencoder/2828)

<div class="topic-metadata">

**Author:** [@Ujjwal2805](https://community.konduit.ai/u/Ujjwal2805)\
**Replies:** 0\
**Last updated:** [September 21, 2023, 7:22am UTC](https://community.konduit.ai/t/lstmautoencoder/2828 "2023-09-21T07:22:01Z")

</div>

deeplearning4j-examples/dl4j-examples/src/main/java/org/deeplearning4j/examples/wip/advanced/modelling/encoderdecoder/EncoderDecoderLSTM.java at master · deeplearning4j/deeplearning4j-examples (github.com) @agibsonccc @…

---

## [DL4J Facenetnn4small2 Face Recognition project](https://community.konduit.ai/t/dl4j-facenetnn4small2-face-recognition-project/2781)

<div class="topic-metadata">

**Author:** [@AUGUSTINE-BEILEL](https://community.konduit.ai/u/AUGUSTINE-BEILEL)\
**Replies:** 5\
**Last updated:** [August 22, 2023, 10:35pm UTC](https://community.konduit.ai/t/dl4j-facenetnn4small2-face-recognition-project/2781 "2023-08-22T22:35:44Z")

</div>

Hello, I am working on a face recognition project using DL4J Core 1.0.0-M2.1 Facenetnn4small2. Despite progress, I am facing accuracy challenges, and my knowledge in transfer learning and pretrained models such as Tenso…

---

## [Custom loss function in ComputationGraph, composing mean square and leakyReLU](https://community.konduit.ai/t/custom-loss-function-in-computationgraph-composing-mean-square-and-leakyrelu/2578)

<div class="topic-metadata">

**Author:** [@EquanimeAugello](https://community.konduit.ai/u/EquanimeAugello)\
**Replies:** 4\
**Last updated:** [June 4, 2023, 12:02pm UTC](https://community.konduit.ai/t/custom-loss-function-in-computationgraph-composing-mean-square-and-leakyrelu/2578 "2023-06-04T12:02:50Z")

</div>

Hello, I’d like to build a custom loss function for a Computation Graph (with a single output) simply defined as the mean square of the leaky ReLU of the difference between output and label. (i.e., a loss function that …

---

## [Retiring the spark and parallelwrapper (minus parallelinference) module](https://community.konduit.ai/t/retiring-the-spark-and-parallelwrapper-minus-parallelinference-module/2539)

<div class="topic-metadata">

**Author:** [@agibsonccc](https://community.konduit.ai/u/agibsonccc)\
**Replies:** 0\
**Last updated:** [April 29, 2023, 11:27pm UTC](https://community.konduit.ai/t/retiring-the-spark-and-parallelwrapper-minus-parallelinference-module/2539 "2023-04-29T23:27:17Z")

</div>

Hello all, The M3 release will be out soon. I wanted the community to know as part of the streamlining of the framework I am continuing to retire modules that I don’t see the community using. I haven’t seen much if any…

---

## [How to use the new generated DL4J artifact in DL4J-examples project?](https://community.konduit.ai/t/how-to-use-the-new-generated-dl4j-artifact-in-dl4j-examples-project/2472)

<div class="topic-metadata">

**Author:** [@yaoyao](https://community.konduit.ai/u/yaoyao)\
**Replies:** 38\
**Last updated:** [April 22, 2023, 5:20am UTC](https://community.konduit.ai/t/how-to-use-the-new-generated-dl4j-artifact-in-dl4j-examples-project/2472 "2023-04-22T05:20:43Z")

</div>

I have built and installed the DL4J project under Linux, and generated the ND4J artifacts like this: Once I use the snapshot in the example project: A test error is reported: How can I use the new generated b…

---

## [Does DL4J support running on Android now?](https://community.konduit.ai/t/does-dl4j-support-running-on-android-now/2489)

<div class="topic-metadata">

**Author:** [@Laurin123](https://community.konduit.ai/u/Laurin123)\
**Replies:** 10\
**Last updated:** [April 18, 2023, 7:19am UTC](https://community.konduit.ai/t/does-dl4j-support-running-on-android-now/2489 "2023-04-18T07:19:26Z")

</div>

I follow the instructions to configure on Android, but the following error will be reported： 04-13 19:49:33.646 9206 9247 E AndroidRuntime: at android.os.Binder.execTransactInternal(Binder.java:1290) 04-13 19:49:33.…

---

## [Performance analysis of DL4J-examples](https://community.konduit.ai/t/performance-analysis-of-dl4j-examples/2463)

<div class="topic-metadata">

**Author:** [@yaoyao](https://community.konduit.ai/u/yaoyao)\
**Replies:** 2\
**Last updated:** [April 9, 2023, 5:44am UTC](https://community.konduit.ai/t/performance-analysis-of-dl4j-examples/2463 "2023-04-09T05:44:54Z")

</div>

I am a beginner of DL4J project. Recently, I profile the dl4j by dl4j-examples project. I want to figure out the following two problems: First, I train the network in org.deeplearning4j.examples.quickstart.modeling.conv…

---

## [Is there any way to extract class labels from the output layer of a FaceNetNN4Small2 computationgraph in DL4J 1.0.0-M2.1](https://community.konduit.ai/t/is-there-any-way-to-extract-class-labels-from-the-output-layer-of-a-facenetnn4small2-computationgraph-in-dl4j-1-0-0-m2-1/2449)

<div class="topic-metadata">

**Author:** [@AUGUSTINE-BEILEL](https://community.konduit.ai/u/AUGUSTINE-BEILEL)\
**Replies:** 5\
**Last updated:** [April 7, 2023, 10:00pm UTC](https://community.konduit.ai/t/is-there-any-way-to-extract-class-labels-from-the-output-layer-of-a-facenetnn4small2-computationgraph-in-dl4j-1-0-0-m2-1/2449 "2023-04-07T22:00:39Z")

</div>

I have the following code but getLabels() seems not to be working for DL4J 1.0.0-M2.1 I am trying to dodge this manual alternative way: String labels = {“Eight”, “Five”, “Four”, “Nine”, “One”, “Seven”, “Six”, “Three”, …

---

## [Simple sequential model example](https://community.konduit.ai/t/simple-sequential-model-example/2453)

<div class="topic-metadata">

**Author:** [@hodophile](https://community.konduit.ai/u/hodophile)\
**Replies:** 6\
**Last updated:** [April 7, 2023, 11:15am UTC](https://community.konduit.ai/t/simple-sequential-model-example/2453 "2023-04-07T11:15:32Z")

</div>

public class SimpleSequentialMlpImport { public static String dataLocalPath; public static void main(String\[\] args) throws Exception { String SIMPLE\_MLP = new ClassPathResource("simple\_mlp.h5").getFile().getPath(); …

---

## [I am asking for help on a Dl4j code to extract class labels from the output layer of a FaceNetNN4Small2 computationgraph](https://community.konduit.ai/t/i-am-asking-for-help-on-a-dl4j-code-to-extract-class-labels-from-the-output-layer-of-a-facenetnn4small2-computationgraph/2447)

<div class="topic-metadata">

**Author:** [@AUGUSTINE-BEILEL](https://community.konduit.ai/u/AUGUSTINE-BEILEL)\
**Replies:** 0\
**Last updated:** [April 6, 2023, 9:11pm UTC](https://community.konduit.ai/t/i-am-asking-for-help-on-a-dl4j-code-to-extract-class-labels-from-the-output-layer-of-a-facenetnn4small2-computationgraph/2447 "2023-04-06T21:11:58Z")

</div>

I have the following code snippet but getLabels() does not work for dl4j version 1.0.0-m2.1. I would not wish to manually use this: String labels = {“Eight”, “Five”, “Four”, “Nine”, “One”, “Seven”, “Six”, “Three”, “Two”,…

---

## [Documentation updates](https://community.konduit.ai/t/documentation-updates/2352)

<div class="topic-metadata">

**Author:** [@agibsonccc](https://community.konduit.ai/u/agibsonccc)\
**Replies:** 1\
**Last updated:** [March 17, 2023, 11:00pm UTC](https://community.konduit.ai/t/documentation-updates/2352 "2023-03-17T23:00:41Z")

</div>

Hello all, I’ve added a new page for required dependencies based on some feedback from the community: https://deeplearning4j.konduit.ai/multi-project/explanation/required-dependencies please let me know if I missed an…

---

## [Dl4j-examples - clean build failure - missing org.deeplearning4j:resources:jar:1.0.0-SNAPSHOT](https://community.konduit.ai/t/dl4j-examples-clean-build-failure-missing-org-deeplearning4jjar-1-0-0-snapshot/2208)

<div class="topic-metadata">

**Author:** [@BrRoBo](https://community.konduit.ai/u/BrRoBo)\
**Replies:** 11\
**Last updated:** [January 27, 2023, 4:42pm UTC](https://community.konduit.ai/t/dl4j-examples-clean-build-failure-missing-org-deeplearning4jjar-1-0-0-snapshot/2208 "2023-01-27T16:42:36Z")

</div>

New to DL4J, I pulled down the entire deeplearning4j-examples for review. Following the basic steps from the tutorials quick-start (Quick Start - Deeplearning4j). Running on Windows 11, JDK 1.8, Maven 4.0 (latest) envi…

---

## [Deeplearning4j running in IntellijIDEA](https://community.konduit.ai/t/deeplearning4j-running-in-intellijidea/2205)

<div class="topic-metadata">

**Author:** [@Bob\_M](https://community.konduit.ai/u/Bob_M)\
**Replies:** 2\
**Last updated:** [January 23, 2023, 4:02am UTC](https://community.konduit.ai/t/deeplearning4j-running-in-intellijidea/2205 "2023-01-23T04:02:21Z")

</div>

Hi I have created a deeplearning4j project in IntellijIDEA When I try to run one of the main classes I get the following error message:- “Cannot run program “C:\\Program Files\\Java\\jdk-19.0.1+10\\bin\\java.exe” (in direc…

[Next page](https://community.konduit.ai/c/uncategorized/1.md?page=1)
