Where communities thrive

  • Join over 1.5M+ people
  • Join over 100K+ communities
  • Free without limits
  • Create your own community
  • 18:28
    strolling-coder edited #8818
  • 18:18
    strolling-coder opened #8818
  • 17:28
    fxbronk commented #8192
  • 15:28
    horschi commented #8739
  • 12:55
    AlexDBlack milestoned #8817
  • 12:55
    AlexDBlack labeled #8817
  • 12:55
    AlexDBlack opened #8817
  • 12:26
    AlexDBlack closed #8684
  • 12:16
    AlexDBlack commented #8684
  • 12:00
    AlexDBlack assigned #8755
  • 11:13
    AlexDBlack commented #8592
  • 11:11
    AlexDBlack assigned #8690
  • 10:26
    atuzhykov closed #8816
  • 10:23
    atuzhykov opened #8816
  • 10:17
    AlexDBlack closed #8760
  • 10:17
    AlexDBlack commented #8760
  • 09:49
    AlexDBlack commented #8811
  • 06:48
    shyrma commented #8592
  • 00:58
    AlexDBlack closed #8739
  • 00:58
    AlexDBlack commented #8739
Raul Feresteanu
From what I understand argMax/argMin seems to return indices along rows/columns but I'd like to know if I can get it to return the row and column indices of the element in question
Raul Feresteanu
Nevermind, I wrote my own helper. Would still be a nice addition to the API
@fortuneNext try Nd4j.setDefaultDataTypes(DataType.DOUBLE,DataType.DOUBLE); put this at the begining of main
I have a question, i tried to import a keras model. the keras model has masking layer plus lstm(64) and dense layers. taking input the padded sequence of one-hot encoded vectors. After importing, i can see it's maskzerolayer then lstm dense layer. Checked each layer weights, the lstm layer weights don't match up, all others match up with python version. The LSTM in dl4j has timestep and features in a swap position compared to python version. The input has been modified accordingly. But it just won't give same result with python verion, any help please?
I run the example code of UIExample,when i go to http://localhost:9000/train, it shows Resource not found,and i search the project ,only two files(log4j ,logback configure file) under the resource folder,where are the needed resource ?
Hi, I'm trying to build regression but have next Exception https://gist.github.com/lemair/2e44f16a3b232019dbf3983db42a22ac
Hello! I'm trying to play around https://github.com/wmeddie/dl4j-gans and to add UIServer server there to observe metrics of the GAN network. But still getting troubles,. First, I got the missing class exceptin, after updating to beta6 I just don't see any localhost:9000 starts for the UI Server, while the calculation is going forward fine
and the second question is how it is designed to use only part of the large jpeg image (2000x3000, 3 chanels) while I instantiate the ImageRecordReader(100, 100, 1). Not clear should I prepare the image by myself in order to use imageRecorderReader correctly: https://stackoverflow.com/questions/60198054/correct-initialization-of-imagerecordreaderlong-height-long-width-long-channe
Hi! I am dl4j begginer, I have a question about scope . Is there some dl4j example for scope of data ?
For example, I teach the A.I below data.
"from 1 to 10 =>legend 1, from 11 to 20 => legend 2, from 21 to 30 => legend 3, from 31 to 40 => legend 4, ... "
Then I can give the scope (a legend) him if a customer input a data.
I am sorry My English is not perfect. I hope you understand it that i want to do.
I have been using computation graph with LSTM layers. But the dependency jars of these have been around 35 jars for linux which sums up to 125 MB. Is there any way to reduce the size by removing the unwanted files from the jar? Most of the jar size where occupied by ".so" files.
Hi, I hope you are all well. I followed the quick start instruction. however, I got an error that the shared utility dependency couldn't resolve. is there any help or recommendation?
if you use eclipse , then you have to import "shared-utilities" project also in your eclipse Package Explorer. I fixed by it.
or you can refer "eclipse/deeplearning4j#8307"
git clone https://github.com/eclipse/deeplearning4j-examples
cd shared-utilities
mvn install
cd ../dl4j-examples
mvn install
Hello. I am trying to train a MultiLayerNetwork using the fit method. I first tried to create an INDArrayDataSetIterator, where I passed the first INDArray as a feature matrix (64 rows and 6 columns) and an INDArray for the label prediction (64 rows and 2 columns).
However, it didn't seem to train correctly as I was constantly getting the same values. I then tried to do it wihtout a dataset iterator but nothing changed.
Any ideas on what i'm doing wrong? I don't think it is related to the network configuration or the learning rate.. Only one parameter of the network output seems to change
Amlesh Sivanantham
hey guys, I'm having some trouble running valgrind to test my java class running some dl4j code. I was following the guide on the old nd4j wiki but the output is not what I expect. They create a script called valgrindJava which essentially wraps the java process into valgrind. I tried running it with my actual arguments, through maven, and standalone without the script. In all cases, it seems that valgrind gives its summary before the java process even runs. Yet in the valgrind logs, I do see the full java command being printed so it is getting it. Hoping someone here understands what the issue could be. Here is the wiki page I was referring to, https://github.com/deeplearning4j/libnd4j/wiki/Debugging-libnd4j
Amlesh Sivanantham
Hey all identified the issue. My java in my path was actually a shell script that then forwarded the call to the actually java binary. Once I passed that in, its correctly being scaned by valgrind
Yuniel Acosta Pérez
I can in the process of transforming my dataset convert a column that contains text into a Vector using Word2Vec. If so, can someone explain to me how
Yuniel Acosta Pérez
I need help please.
@yuniel-acosta You can, see the example in https://deeplearning4j.org/docs/latest/deeplearning4j-nlp-word2vec you the you just need to input the information from your file instead of raw_sentences.txt
Anybody can suggest some good tutorial on how to setup a simple reinforcement learning environment in DL4J? Examples require frameworks, the toy sample is not documented and object involved are not immediate to understand event diving in the code.
new to DL4J
trying to do the serup
getting below exception when i try to run the CSVExample.java in IntelliJ
i completed the Maven clean install
any help plz?
@sskmaestro As you can see, the files on the azure cloud where they are supposed to be hosted are no longer available, so the link is broken. I solved searching those files and caching myself in my local folders. e.g., C:\Users\myself\dl4j-examples-data\dl4j-examples\nlp\raw_sentences.txt
You can find the local path of IrisData.zip in project "shared-utilities*/.../DownloaderUtility.java, in this case:
IRISDATA("IrisData.zip", "datavec-examples", "bb49e38bb91089634d7ef37ad8e430b8", "1KB"),
so it would be:
Unfortunately I can't find the mirror I used.
@artsakenos I dont see the IrisData.zip under \dl4j-examples-data\dl4j-examples\datavec-examples\
Manish Patel
Hi, is there a way for ImageRecordReader to autodetect the correct number of channels, e.g. from the first image in the data set?

@sskmaestro Yes, what I meant you have to cache it by yourself on that folder, i.e., download it and put it there. For example this link should have an iris data folder: https://archive.ics.uci.edu/ml/datasets/Iris

I'm so sad Java Developers and tools for Machine Learning always seem just like they're being abandoned.


Hi, I'm debugging an application where physical memory usage grows indefinitely, resulting in OutOfMemory errors. The Errors may occur in a few places, but the ultimate result is "Physical memory usage is too high: physicalBytes(40238M) > maxPhysicalBytes(40050m). It usually takes around 1 million requests to a tomcat app where the ComputationGraphs and DataSetIterator live.

I cannot debug the above application on a linux machine where I can easily change code and iterate quickly. I have created a toy app based on one of the dl4j examples. There is no tomcat, it just loads the net built in CnnSentenceClassificationExample (I used the same training code there), then loops over the DataISetIterator and call net.output on each batch.

I noticed that if logging Pointer.physicalBytes(), in the toy app it goes up until a certain point. Then there is a few second pause, and the totalBytes number drops. Once I see this happen, I see that it happens each time the value gets to a certain max value.

In the tomcat app logs, I don't see the value ever go down. I wasn't logging physical bytes when I saw the OOM, and will do more tests. But, I'm currently trying to pin down where in the dl4j, nd4j, javacpp code is running during this pause (which appears to be garbage collection for native memory). I'd like to find that to see if for some reason that same code segment is being skipped in my tomcat app. Any advice here would be appreciated, thanks.

The OutOfMemory errors generally occur in <init>FloatPointer
Samuel Audet
@tc64 It's possible that garbage collection is taking more time with Tomcat because of other applications running in the container. Try to increase the number of retries to System.gc(): http://bytedeco.org/javacpp/apidocs/org/bytedeco/javacpp/Pointer.html#maxRetries
Hello, How to change model in interface? Example:
Hi , we can use deeplearning4j for analysis vedio !!

I'm seeing something interesting in Nd4j's getRow. When doing getRow(0) it appears to return all of the data, not just the first row. Code snippet:
val shape = outMat.shape()
val out = which + ";" + (0L until shape(0)).map(ll=>{
val data = outMat.getRow(ll).data().asDouble()

outMat is an INDArray 2D array with size (5,256). Obviously using Scala, and not the latest version of DL4J (1.0.0-beta2), so forgive me if this has been seen before!

this code snippet yields:

Martin Krybus
Hello guys, could someone direct me please ? Im using QLearningDiscreteConv to learn car drive straight road, rewards are made in the following way: if car deviate from middle of the road he get -0.1, either can get closer to the middle so he gets 0.1, the result should be to learn car drive straight road trying to stay in the middle, only 2 action, turn left and turn right 4 degrees, lower epsilon is the worse results the car gets, in other words, if he tries random action he is better that take action based on values from q-table, what am i doing wrong? Typically if policy.EpsGreedy - EP: is very low number he typically stick to one action, very frustrating, as input im using immediate surroundings of the car - to optimize training process
Rural Hunter

Hi, I have a question regarding using external error: https://github.com/eclipse/deeplearning4j-examples/blob/master/dl4j-examples/src/main/java/org/deeplearning4j/examples/misc/externalerrors/MultiLayerNetworkExternalErrors.java
If my nn is like this:

MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder()
            .updater(new Nesterovs(0.001,0.9))
            .layer(0, new DenseLayer.Builder().nOut(20).build())
            .layer(1, new DenseLayer.Builder().activation(Activation.SOFTMAX).nOut(4).build())

To calculate the gradient, should I use the vanila error or the error after softmax activation in the net.backpropGradient() function?

what is thingsboard exactly??
Hello, I have question about random seed. I am new to GPU training, so this will not be my last question :). If I set .seed(123) in FineTuneConfiguration and try to train model on CPU, it works as it should. With every new run with everything same i have same results. But on GPU are results every time different (with same seed). I also tried Nd4J.getRandom().setSeed() method, but didn't help. On both machines I have same code. Do you know, what can be possible wrong? Am I missing something?