# Latest **URL:** https://community.konduit.ai/latest.md?page=1 [Latest](https://community.konduit.ai/latest.md) · [Categories](https://community.konduit.ai/categories.md) **Page:** 2 --- ## [Does DL4J support cuda 12.x?](https://community.konduit.ai/t/does-dl4j-support-cuda-12-x/3363)
**Author:** [@Booker](https://community.konduit.ai/u/Booker)\ **Replies:** 3\ **Last updated:** [May 30, 2025, 7:01am UTC](https://community.konduit.ai/t/does-dl4j-support-cuda-12-x/3363 "2025-05-30T07:01:04Z")
the highest version is 11.6 in Index of /repositories/snapshots/org/nd4j --- ## [Empty features in time series sequences](https://community.konduit.ai/t/empty-features-in-time-series-sequences/3365)
**Author:** [@xcocco](https://community.konduit.ai/u/xcocco)\ **Replies:** 0\ **Last updated:** [May 22, 2025, 1:48pm UTC](https://community.konduit.ai/t/empty-features-in-time-series-sequences/3365 "2025-05-22T13:48:23Z")
I’m trying to build a Recurrent Neural Network for a regression problem, my dataset (csv file with a header) has this structure f1,f2,f3,f4,label and I’m using CSVNLinesSequenceRecordReader to read 5 lines to group into … --- ## [Does DL4J support lora training?](https://community.konduit.ai/t/does-dl4j-support-lora-training/3362)
**Author:** [@Booker](https://community.konduit.ai/u/Booker)\ **Replies:** 1\ **Last updated:** [May 20, 2025, 12:22pm UTC](https://community.konduit.ai/t/does-dl4j-support-lora-training/3362 "2025-05-20T12:22:20Z")
Does DL4J support lora training? for normal DL such yolo11 etc or LLM. --- ## [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)
**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")
I can’t find it on the official website https://deeplearning4j.konduit.ai/ --- ## [DL4J for Termux](https://community.konduit.ai/t/dl4j-for-termux/3349)
**Author:** [@LobsterMan](https://community.konduit.ai/u/LobsterMan)\ **Replies:** 1\ **Last updated:** [April 5, 2025, 9:14am UTC](https://community.konduit.ai/t/dl4j-for-termux/3349 "2025-04-05T09:14:40Z")
Does DL4J now run on Android Termux? It was several years ago I tried to write actual code using DL4J on Termux’s Java, but although it would compile, running the compiled code would always give an error about some depe… --- ## [Is DL4J suitable for fine-tuning hugging face deep learning models?](https://community.konduit.ai/t/is-dl4j-suitable-for-fine-tuning-hugging-face-deep-learning-models/3346)
**Author:** [@amano](https://community.konduit.ai/u/amano)\ **Replies:** 7\ **Last updated:** [April 1, 2025, 4:34am UTC](https://community.konduit.ai/t/is-dl4j-suitable-for-fine-tuning-hugging-face-deep-learning-models/3346 "2025-04-01T04:34:35Z")
The latest hugging face deep learning models are in safetensors format. I’m new to machine learning and deep learning. I understand basic high-level concepts, but I don’t know math or technical details. For example, I k… --- ## [Predicting with a keras model: data types and byte orders](https://community.konduit.ai/t/predicting-with-a-keras-model-data-types-and-byte-orders/3348)
**Author:** [@Phobrain](https://community.konduit.ai/u/Phobrain)\ **Replies:** 2\ **Last updated:** [March 31, 2025, 10:09pm UTC](https://community.konduit.ai/t/predicting-with-a-keras-model-data-types-and-byte-orders/3348 "2025-03-31T22:09:29Z")
I verified that I need to reverse byte order of predictions in keras python to be read in java. Now that I’ve loaded a trained .keras model in DL4J and made some predictions, these naive questions arise: Is byte order … --- ## [How to create an ndArray using the byte\[\] obtained by ndArray.data().asBytes()?](https://community.konduit.ai/t/how-to-create-an-ndarray-using-the-byte-obtained-by-ndarray-data-asbytes/3340)
**Author:** [@cqiaoYc](https://community.konduit.ai/u/cqiaoYc)\ **Replies:** 3\ **Last updated:** [March 18, 2025, 7:19am UTC](https://community.konduit.ai/t/how-to-create-an-ndarray-using-the-byte-obtained-by-ndarray-data-asbytes/3340 "2025-03-18T07:19:20Z")
Why is it that for the byte array dataBuffer created by Nd4j.createTypedBuffer(bytes, DataType.FLOAT) , when using Nd4j.create(dataBuffer, shape); to create an ndarray , the values of the ndarray are float numbers that a… --- ## [TicTacToeData Op Code Error](https://community.konduit.ai/t/tictactoedata-op-code-error/3338)
**Author:** [@mrenzi](https://community.konduit.ai/u/mrenzi)\ **Replies:** 1\ **Last updated:** [March 14, 2025, 1:37am UTC](https://community.konduit.ai/t/tictactoedata-op-code-error/3338 "2025-03-14T01:37:28Z")
Hi - I am trying to get the TicTacToe dl4j example working. Since I don’t have the data file example, I’m using TicTacToeData (part of the example package) to generate the data file. It is failing with an op code excep… --- ## [Where to Find DL4J Example Data](https://community.konduit.ai/t/where-to-find-dl4j-example-data/3339)
**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")
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… --- ## [Newbie. Need info on YOLO](https://community.konduit.ai/t/newbie-need-info-on-yolo/3336)
**Author:** [@galera](https://community.konduit.ai/u/galera)\ **Replies:** 1\ **Last updated:** [February 24, 2025, 9:54pm UTC](https://community.konduit.ai/t/newbie-need-info-on-yolo/3336 "2025-02-24T21:54:46Z")
I am newbie using deepLearning4J. I try to develop an application in java looking for face of animals (birds, mamals, …) and i see that we can just access to TinyYOLO which contains only 20 classes. My question is: How t… --- ## [How to perform mixed-precision training?](https://community.konduit.ai/t/how-to-perform-mixed-precision-training/3335)
**Author:** [@cqiaoYc](https://community.konduit.ai/u/cqiaoYc)\ **Replies:** 1\ **Last updated:** [February 24, 2025, 3:36am UTC](https://community.konduit.ai/t/how-to-perform-mixed-precision-training/3335 "2025-02-24T03:36:16Z")
May I ask where I can find an example of mixed precision training? I converted the feature array and label array to half precision, and set the data type to half precision in the network configuration, but it fails to co… --- ## [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)
**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")
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… --- ## [Cant find out how to fix DL4JInvalidInputException](https://community.konduit.ai/t/cant-find-out-how-to-fix-dl4jinvalidinputexception/3328)
**Author:** [@cho](https://community.konduit.ai/u/cho)\ **Replies:** 5\ **Last updated:** [February 21, 2025, 6:23am UTC](https://community.konduit.ai/t/cant-find-out-how-to-fix-dl4jinvalidinputexception/3328 "2025-02-21T06:23:07Z")
So I’m new to machine learning and I’ve tried to begin training a model but have been getting the org.deeplearning4j.exception.DL4JInvalidInputException error for a day or two. I’ve tried setting builder.setInputType(In… --- ## [Can DL4J export an ONNX format model?](https://community.konduit.ai/t/can-dl4j-export-an-onnx-format-model/3256)
**Author:** [@Glowberry](https://community.konduit.ai/u/Glowberry)\ **Replies:** 3\ **Last updated:** [February 20, 2025, 1:54pm UTC](https://community.konduit.ai/t/can-dl4j-export-an-onnx-format-model/3256 "2025-02-20T13:54:09Z")
I want to export the ONNX format model from MultiLayerNetwork, but only multiLayerNetwork.save(new File("model.zip")); support, and it can only export a zip file, not ONNX. I trained the model and want to use in anothe… --- ## [Data Forecasting Model Sequence to Sequence](https://community.konduit.ai/t/data-forecasting-model-sequence-to-sequence/3326)
**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")
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)
**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")
I try to stop logging using deeplearningFor4J creating a logback.xml file: %d{yyyy-MM-dd HH:mm:ss} %-5level %logger{36} - %msg%n \ **Author:** [@thneeb](https://community.konduit.ai/u/thneeb)\ **Replies:** 6\ **Last updated:** [February 5, 2025, 9:59am UTC](https://community.konduit.ai/t/need-a-neural-network-configuration-for-pong-atari-games/3316 "2025-02-05T09:59:16Z") I tried a lot of different WeightInits and Activation functions, but I don’t get the network to learn. The gradients are from the initialization in my opinion very small 1e-3 to 1e-5. The starting q-values are okay betwe… --- ## [Missing package](https://community.konduit.ai/t/missing-package/3306)
**Author:** [@Ferra](https://community.konduit.ai/u/Ferra)\ **Replies:** 6\ **Last updated:** [January 23, 2025, 10:14pm UTC](https://community.konduit.ai/t/missing-package/3306 "2025-01-23T22:14:13Z")
I always get the error of: Error occurred during initialization of boot layer java.lang.module.FindException: Error reading module: C:\\Users\\Ferra.m2\\repository\\org\\deeplearning4j\\deeplearning4j-modelimport\\1.0.0-M2\\de… --- ## [Not able to train my Connect4 Network](https://community.konduit.ai/t/not-able-to-train-my-connect4-network/3313)
**Author:** [@thneeb](https://community.konduit.ai/u/thneeb)\ **Replies:** 1\ **Last updated:** [January 23, 2025, 10:11pm UTC](https://community.konduit.ai/t/not-able-to-train-my-connect4-network/3313 "2025-01-23T22:11:57Z")
Hello together. I am new here and new to Neural Networks and new to dl4j. I am interested in Deep Reinforcement Learning, but the structure which used to be with dl4j is gone :frowning: . But I created my own framework … --- ## [New backend development for Ascend NPU](https://community.konduit.ai/t/new-backend-development-for-ascend-npu/3308)
**Author:** [@luentong](https://community.konduit.ai/u/luentong)\ **Replies:** 1\ **Last updated:** [January 7, 2025, 9:47am UTC](https://community.konduit.ai/t/new-backend-development-for-ascend-npu/3308 "2025-01-07T09:47:58Z")
Hi! I’m new to DL4j. Our Ascend NPU team wants to add support for DL4j. So far, I think the way is doing our own NPU implementation of backend, just like nd4j-tvm or nd4j-tensorflow. wondering what kinds documents or co… --- ## [SameDiff optimizer](https://community.konduit.ai/t/samediff-optimizer/3297)
**Author:** [@roman](https://community.konduit.ai/u/roman)\ **Replies:** 9\ **Last updated:** [December 12, 2024, 7:48am UTC](https://community.konduit.ai/t/samediff-optimizer/3297 "2024-12-12T07:48:03Z")
Hello. I am trying to similar to tensoflow working code with SameDiff. So, tenflow code: obs\_ph = tf.placeholder(shape=(None, obs\_dim\[0\]), dtype=tf.float32, name='obs') act\_ph = tf.placeholder(shape=(None, ), d… --- ## [Working with arrays of data](https://community.konduit.ai/t/working-with-arrays-of-data/3299)
**Author:** [@INotSleep](https://community.konduit.ai/u/INotSleep)\ **Replies:** 1\ **Last updated:** [December 12, 2024, 7:37am UTC](https://community.konduit.ai/t/working-with-arrays-of-data/3299 "2024-12-12T07:37:15Z")
Hello everyone! I want to create some NN, that will process array of data and return new array of data. How i can do that? For example: INPUT 1000 elements 9 features each OUTPUT: 10 elements 2 features each --- ## [Is there any example for doing policy gradient calculation with dl4j/rl4j?](https://community.konduit.ai/t/is-there-any-example-for-doing-policy-gradient-calculation-with-dl4j-rl4j/240)
**Author:** [@RuralHunter](https://community.konduit.ai/u/RuralHunter)\ **Replies:** 14\ **Last updated:** [December 11, 2024, 6:34am UTC](https://community.konduit.ai/t/is-there-any-example-for-doing-policy-gradient-calculation-with-dl4j-rl4j/240 "2024-12-11T06:34:06Z")
I can not find any. Since dl4j embeds the activation function in the layer, it seems difficult to calculate the gradient externally and put it back in dl4j network. --- ## [Load CSV data and apply transformation](https://community.konduit.ai/t/load-csv-data-and-apply-transformation/3294)
**Author:** [@nilay](https://community.konduit.ai/u/nilay)\ **Replies:** 1\ **Last updated:** [December 2, 2024, 11:34pm UTC](https://community.konduit.ai/t/load-csv-data-and-apply-transformation/3294 "2024-12-02T23:34:52Z")
I want to load data from csv and below is my code public DataSet loadData(int batchSize, int numClasses) throws IOException, InterruptedException { // Load CSV file as a resource from classpath ClassPathResource res… --- ## [How to dynamically load the required batch into GPU memory?](https://community.konduit.ai/t/how-to-dynamically-load-the-required-batch-into-gpu-memory/3290)
**Author:** [@cqiaoYc](https://community.konduit.ai/u/cqiaoYc)\ **Replies:** 2\ **Last updated:** [November 26, 2024, 1:05am UTC](https://community.konduit.ai/t/how-to-dynamically-load-the-required-batch-into-gpu-memory/3290 "2024-11-26T01:05:50Z")
When the dataset is large, memory capacity is sufficient, but GPU memory (VRAM) is limited, how to efficiently utilize VRAM? Store the sample data in memory first, and during training, dynamically load the required batc… --- ## [How do we get a new release of deeplearning4j?](https://community.konduit.ai/t/how-do-we-get-a-new-release-of-deeplearning4j/3289)
**Author:** [@matthewcummings](https://community.konduit.ai/u/matthewcummings)\ **Replies:** 2\ **Last updated:** [November 25, 2024, 5:13am UTC](https://community.konduit.ai/t/how-do-we-get-a-new-release-of-deeplearning4j/3289 "2024-11-25T05:13:01Z")
I need a new release with updated dependencies, but I see that there hasn’t been a new public release since https://mvnrepository.com/artifact/org.deeplearning4j/deeplearning4j-core/1.0.0-M2.1. I only need a build with … --- ## [A very simple case of linear regression](https://community.konduit.ai/t/a-very-simple-case-of-linear-regression/3285)
**Author:** [@roman](https://community.konduit.ai/u/roman)\ **Replies:** 2\ **Last updated:** [November 22, 2024, 7:20am UTC](https://community.konduit.ai/t/a-very-simple-case-of-linear-regression/3285 "2024-11-22T07:20:05Z")
Hello! Could somebody please help me with a very simple case of linear regression and DL4j? I have just spent already several hours trying to reach what I did in python and tensorflow in a half of an hour. So, I try to … --- ## [INDArray in ND4J 1.0.0-M2.1 slower on Android than 1.0.0-beta6](https://community.konduit.ai/t/indarray-in-nd4j-1-0-0-m2-1-slower-on-android-than-1-0-0-beta6/3277)
**Author:** [@panassevich](https://community.konduit.ai/u/panassevich)\ **Replies:** 1\ **Last updated:** [November 13, 2024, 1:48pm UTC](https://community.konduit.ai/t/indarray-in-nd4j-1-0-0-m2-1-slower-on-android-than-1-0-0-beta6/3277 "2024-11-13T13:48:41Z")
Hello. I wrote a neural network class SCN (Stochastic Configuration Network) on Kotlin in an Android application for research purposes. The n-dimensional arrays from ND4J were very useful to me. Initially, I imported DL4… --- ## [Prediction Makes No Sense](https://community.konduit.ai/t/prediction-makes-no-sense/3275)
**Author:** [@AustinDart](https://community.konduit.ai/u/AustinDart)\ **Replies:** 1\ **Last updated:** [November 13, 2024, 12:37am UTC](https://community.konduit.ai/t/prediction-makes-no-sense/3275 "2024-11-13T00:37:56Z")
Hey, I’m new to the whole Machine Learning scene, and I’m playing around with DL4J. I’m trying to get it to predict the classification of an Iris based on the info given (a very common first program with machine learning… [Previous page](https://community.konduit.ai/latest.md) [Next page](https://community.konduit.ai/latest.md?page=2)