deeplearning4j | training deep learning models using the JVM | Machine Learning library

You need to use the same normalizer data for both training and prediction. Otherwise it will use wrong statistics when transforming your data.

The way you are currently doing it, results in data that looks very different from the training data, that is why you get such a different result.

CanvasFrame tries to do gamma correction by default because it's typically needed by cameras used for CV, but cheap webcams usually output gamma corrected images, so make sure to let CanvasFrame know about it this way:

There are many ways to reduce the size of your jar depending on what your use case is. We cover this more recently in our docs, but I'll summarize some things to try here:

1. DL4j is heavily based on javacpp. You can add -Djavacpp.platform=$YOUR_PLATFORM (linux-x86_64, windows-x86_64,..) to your build to reduce the number of native dependencies in there.

2. If you are using deeplearning4j-core, that includes a lot of extra dependencies you may not need. In this case, you may only need deeplearning4j-nn for the configuration. The same goes for if you are using only samediff, you do not need the dl4j apis. I don't know enough about your use case to confirm what you do and don't need though.

3. If you are deploying on an embedded platform, we also have the ability to reduce the number of supported operations and data types now as well. This feature is mainly for advanced users right now (involves building from source) but if you think that could also be applicable despite the first 2, please do confirm and I can try to clarify that a bit.

This function samples from the distribution, instead of simply returning the most probable character class.

That also means that you aren't getting the most likely character, instead, you are getting a random character with the probability that the given probability distribution defines.

This works by first getting a random value between 0 and 1 from a uniform distribution (rng.nextDouble()) and then finding where that value falls in the given distribution.

You can imagine it to be something like this (if your had only a to f in your alphabet):

Firstly, always use Nd4j.create(..) for ndarrays. Never use the implementation. That allows you to safely create ndarrays that will work whether you use cpus or gpus.

2nd: Always use the RecordReaderDataSetIterator's builder rather than the constructor. It's very long and error prone.

That is why we made the builder in the first place.

Your NullPointer actually isn't coming from where you think it is. it's due to how you're creating the ndarray. There's no data type or anything so it can't know what to expect. Nd4j.create(..) will properly setup the ndarray for you.

Beyond that you are doing things the right way. The record reader handles the batching for you.

So, adding this code solved my problem:

Well, I couldn't work out how to make log4j function. I tried what was suggested in the comments, such as including slf4j-log4j12, or nd4j-x86.

Sometimes the best way to solve a problem is to remove it instead: I stopped trying to get log4j to function and went with nd4j-native.

By default there is no limit. That means it will add all words it finds to the vocabulary.

Also note, the examples you linked to are over 4 years old. I suggest you use the official examples: https://github.com/eclipse/deeplearning4j-examples

It looks like you modified something? Sorry if I'm not quite following what you did, but that error message indicates a missing pom.xml. The specific steps you follow are:

1. Clone the repository