Open SunnyPage opened 1 year ago
Hello, you might be getting this error because there was a crash while writing the neural network file, which has corrupted the file and thus cannot be read from. Try to save the file again, and then open it.
Many thanks for the help.
I also added to ImagePatchesLayer-save()->writer.write(this.returnGradient + "\n"); I think it was skipped. And also added to MultiHeadAttentionLayer->read()-> int[] size = new int[2]; size[0] = layer.mask.getRow(); size[1] = layer.sizeAttention; layer.initialize(size);
I am trying to create speech recognition for Georgian language. I tried to train 190 sentence audio files. After 8 hours of training on i7-8565U. Successfully trained. I used 12 Head Attention instead of 4 heads.
I have one question. Under what license is this project distributed?
Thanks for the tips. I have also added a standard license to the project, use it for your purposes.
Hello, I discovered your library a few days ago. A very good library. I'm trying to train a Visual transformer. I started testing TestVIT. "Save" network works. But when I tried "Load" - I get an error! Please help fix...
NeuralNetwork network = NeuralNetwork.read(new Scanner(new File("capsnet.txt"))) .setOptimizer(new AdamOptimizer()) .setFunctionLoss(new FunctionLoss.MSE()) .create();
java.lang.NumberFormatException: For input string: "0.0014131109" at java.base/java.lang.NumberFormatException.forInputString(NumberFormatException.java:67) at java.base/java.lang.Integer.parseInt(Integer.java:665) at java.base/java.lang.Integer.parseInt(Integer.java:781) at java.base/java.util.stream.ReferencePipeline$4$1.accept(ReferencePipeline.java:214) at java.base/java.util.Spliterators$ArraySpliterator.forEachRemaining(Spliterators.java:1006) at java.base/java.util.stream.AbstractPipeline.copyInto(AbstractPipeline.java:509) at java.base/java.util.stream.AbstractPipeline.wrapAndCopyInto(AbstractPipeline.java:499) at java.base/java.util.stream.AbstractPipeline.evaluate(AbstractPipeline.java:575) at java.base/java.util.stream.AbstractPipeline.evaluateToArrayNode(AbstractPipeline.java:260) at java.base/java.util.stream.IntPipeline.toArray(IntPipeline.java:562) at nnarrays.NNMatrix.read(NNMatrix.java:314)