Comments (1)
Hi @fdebeyan, unfortunately I wasn't able to replicate this issue - can you try the configuration below by copying it into the GUI and let me know how it goes? If I'm not mistaken, this is the output layer configuration you're having an issue with.
weka.classifiers.functions.RnnSequenceClassifier -S 1 -tBPTTBackward 25 -tBPTTForward 25 -cache-mode FILESYSTEM -early-stopping "weka.dl4j.earlystopping.EarlyStopping -maxEpochsNoImprovement 0 -valPercentage 0.0" -normalization "Standardize training data" -iterator "weka.dl4j.iterators.instance.sequence.text.rnn.RnnTextEmbeddingInstanceIterator -stopWords \"weka.dl4j.text.stopwords.Dl4jRainbow \" -tokenPreProcessor \"weka.dl4j.text.tokenization.preprocessor.CommonPreProcessor \" -tokenizerFactory \"weka.dl4j.text.tokenization.tokenizer.factory.NGramTokenizerFactory -NMax 3 -NMin 1 -delimiters \\\" \\\\r\\\\n\\\\t.,;:\\\\\\\'\\\\\\\"()?!\\\"\" -truncationLength 2 -wordVectorLocation /Users/rhyscompton/Documents/git/wekaDeeplearning4j/src/test/resources/GoogleNews-vectors-negative300-SLIM.bin.gz -bs 1" -iteration-listener "weka.dl4j.listener.EpochListener -eval true -n 5" -layer "weka.dl4j.layers.LSTM -gateActivation \"weka.dl4j.activations.ActivationSigmoid \" -nOut 2 -activation \"weka.dl4j.activations.ActivationReLU \" -name \"LSTM layer\"" -layer "weka.dl4j.layers.RnnOutputLayer -lossFn \"weka.dl4j.lossfunctions.LossBinaryXENT \" -nOut 2 -activation \"weka.dl4j.activations.ActivationSigmoid \" -name \"RnnOutput layer\"" -logConfig "weka.core.LogConfiguration -append true -dl4jLogLevel WARN -logFile /Users/rhyscompton/wekafiles/wekaDeeplearning4j.log -nd4jLogLevel INFO -wekaDl4jLogLevel INFO" -config "weka.dl4j.NeuralNetConfiguration -biasInit 0.0 -biasUpdater \"weka.dl4j.updater.Sgd -lr 0.001 -lrSchedule \\\"weka.dl4j.schedules.ConstantSchedule -scheduleType EPOCH\\\"\" -dist \"weka.dl4j.distribution.Disabled \" -dropout \"weka.dl4j.dropout.Disabled \" -gradientNormalization None -gradNormThreshold 1.0 -l1 NaN -l2 NaN -minimize -algorithm STOCHASTIC_GRADIENT_DESCENT -updater \"weka.dl4j.updater.Adam -beta1MeanDecay 0.9 -beta2VarDecay 0.999 -epsilon 1.0E-8 -lr 0.001 -lrSchedule \\\"weka.dl4j.schedules.ConstantSchedule -scheduleType EPOCH\\\"\" -weightInit XAVIER -weightNoise \"weka.dl4j.weightnoise.Disabled \"" -numEpochs 2 -numGPUs 1 -averagingFrequency 10 -prefetchSize 24 -queueSize 0 -zooModel "weka.dl4j.zoo.CustomNet -channelsLast false -pretrained NONE"
Change the wordVectorLocation
to one on your machine. The one I used can be downloaded from here
I tested this on a tiny version of the IMDB dataset (attached) and it worked without a hitch:
from wekadeeplearning4j.
Related Issues (20)
- how to apply 1-d convolution? HOT 4
- Visualise Filters and Feature Maps.
- after installed, it shows could not find wekadeeplearning4j? HOT 5
- Bug: cannot run textembeddings in 1.5.14 HOT 3
- Is there a way to architect a bidirectional RNN? HOT 1
- Its possible to use Binary FastText model instead of word2vec?
- Problem For Label classes inferred using label generator
- How to modify Output Layer in Pretrained Models such as Dl4JResNet50
- Latest CUDA version is 11.1 HOT 2
- wekaDeeplearning4j i386 HOT 1
- Unable to change NGramTokenizerFactory properties (GUI) HOT 2
- Add Support for loading and Keras Model from `.h5` file
- Plot Top Losses
- Default Image Data Augmentation
- EfficientNet model return error
- NaNs in model output, likely caused by arithmetic underflow HOT 1
- RnnSequenceClassifier has null model after deserialization
- cudaGetSymbolAddress
- Stuck in Building model on training data HOT 3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from wekadeeplearning4j.