A general forum for machine learning and deep learining questions, focused on DL4J/ND4J
the css store in the site can't access from China?
We're just hosted on discourse's cloud..checking it it doesn't look like it's down: https://updownradar.com/status/discourse.org
I'm guessing something changed there, not sure
From what I know other chinese users haven't had issues there
Try a VPN and see if that's the problem
If so, this is new. I haven't heard about this. It might be a recent change the discourse team did
Checking: https://www.comparitech.com/privacy-security-tools/blockedinchina/ it appears discourse.org isn't blocked either
Your problem seems isolated to you somewhere
If there's a particular domain that comes up that's a problem let me know
I wonder why I'm not affected by this..I'm using chrome
Hm, just tried it on firefox no issues
it work
Thanks
Hey There just wanted to share references for open source projects i share on twitter to the community here , check my github profile at github.com/aah20 and my twitter at https://twitter.com/Ahmed_Hassan_73
Hi all, I am new to ML and I am learning it by creating a project. I want to create a handwritten app, and for fun I want to do it for others language than english, I chose French and Arabic as I speak both> I am wondering how to create a dataset ? all the steps and how many sentences or words should I collect ? Thanks for you advices
so im trying to mvn clean install it, but i dont see there is any pom.xml in dl4j-examples folder
1 reply
is there something that i missed?
im following tutorial here -> deeplearning4j.konduit.ai
Your problem isn't really clear. Your problem could be anything ranging from "how do I use maven and intellij" to "I want to build from source" the home page doesn't have anything specific on it. As dl4j is a library and not a desktop application you don't "install it" you "include it as a library in your favorite IDE or project"
Hi all, I am a little new to dl4j. So I had been trying to run a unet model. After the line computaional_graph.fit() I get the following error
Exception in thread "main" java.lang.RuntimeException: std::bad_alloc
at org.nd4j.nativeblas.Nd4jCpu.mallocHost(Native Method)
at org.nd4j.linalg.cpu.nativecpu.CpuMemoryManager.allocate(CpuMemoryManager.java:48)
at org.nd4j.linalg.api.memory.abstracts.Nd4jWorkspace.alloc(Nd4jWorkspace.java:421)
at org.nd4j.linalg.api.memory.abstracts.Nd4jWorkspace.alloc(Nd4jWorkspace.java:320)
at org.nd4j.linalg.cpu.nativecpu.buffer.BaseCpuDataBuffer.<init>(BaseCpuDataBuffer.java:492)
at org.nd4j.linalg.cpu.nativecpu.buffer.FloatBuffer.<init>(FloatBuffer.java:68)
at org.nd4j.linalg.cpu.nativecpu.buffer.DefaultDataBufferFactory.create(DefaultDataBufferFactory.java:329)
at org.nd4j.linalg.factory.Nd4j.createBuffer(Nd4j.java:1467)
at org.nd4j.linalg.api.ndarray.BaseNDArray.<init>(BaseNDArray.java:324)
at org.nd4j.linalg.cpu.nativecpu.NDArray.<init>(NDArray.java:191)
at org.nd4j.linalg.cpu.nativecpu.CpuNDArrayFactory.createUninitialized(CpuNDArrayFactory.java:226)
at org.nd4j.linalg.factory.Nd4j.createUninitialized(Nd4j.java:4364)
at org.deeplearning4j.nn.layers.convolution.ConvolutionLayer.preOutput(ConvolutionLayer.java:442)
at org.deeplearning4j.nn.layers.convolution.ConvolutionLayer.activate(ConvolutionLayer.java:505)
at org.deeplearning4j.nn.graph.vertex.impl.LayerVertex.doForward(LayerVertex.java:110)
at org.deeplearning4j.nn.graph.ComputationGraph.ffToLayerActivationsInWS(ComputationGraph.java:2135)
at org.deeplearning4j.nn.graph.ComputationGraph.computeGradientAndScore(ComputationGraph.java:1372)
at org.deeplearning4j.nn.graph.ComputationGraph.computeGradientAndScore(ComputationGraph.java:1341)
at org.deeplearning4j.optimize.solvers.BaseOptimizer.gradientAndScore(BaseOptimizer.java:174)
at org.deeplearning4j.optimize.solvers.StochasticGradientDescent.optimize(StochasticGradientDescent.java:61)
at org.deeplearning4j.optimize.Solver.optimize(Solver.java:52)
at org.deeplearning4j.nn.graph.ComputationGraph.fitHelper(ComputationGraph.java:1165)
at org.deeplearning4j.nn.graph.ComputationGraph.fit(ComputationGraph.java:1115)
at org.deeplearning4j.nn.graph.ComputationGraph.fit(ComputationGraph.java:1082)
at org.deeplearning4j.nn.graph.ComputationGraph.fit(ComputationGraph.java:1018)
at org.deeplearning4j.nn.graph.ComputationGraph.fit(ComputationGraph.java:1006)
at activeSegmentation.deepLearning.UNet1.run(UNet1.java:111)
at activeSegmentation.deepLearning.UNet1.main(UNet1.java:287)I guess it is the memory error right? Is there any way to solve it or is it limited by the laptop configurations
@Purva-Chaudhari can you please migrate your questions to the community forum? https://community.konduit.ai/ at first guess it's an out of memory.
All, I am excited to invite you to the Joint OGC OSGeo ASF Virtual Code Sprint that is taking place 7:00am - 5:30pm EST from March 8th to 10th. The code sprint will focus on open standards and open source software. This will be a great opportunity to engage with software developers that might be interested in integrating Deeplearning4J into their Java-based software projects. The extended deadline for registration is 7:00am EST on March 8th. Please register at https://portal.ogc.org/public_ogc/register/220225asf_codesprint.php
I want config a multi-LSTM net with attentions like:
NeuralNetConfiguration.ListBuilder listBuilder = nncBuilder.list();
int nIn = featuresCount;
for (int i = 0; i < this.rnnNeurons.length; ++i) {
listBuilder.layer(i, new LSTM.Builder().activation(Activation.SOFTSIGN).nIn(nIn).nOut(rnnNeurons[i]).build());
nIn = rnnNeurons[i];
int nhead=8;
listBuilder.layer(i, new RecurrentAttentionLayer.Builder().activation(Activation.SOFTSIGN).nIn(nIn).nOut(nIn).nHeads(nhead).projectInput(true).build());
}how should I set the param: setInputType(InputType.recurrent(size))?
Hi everyone, is it possible to import PyTorch model with Deeplearning4j? I can only find examples for Tensorflow/Keras https://github.com/eclipse/deeplearning4j-examples/tree/master/tensorflow-keras-import-examples . If it's possible, could you show me some instructions, thank you in advance!