Adam Pocock

There's a LeNet 5 style MNIST model here - https://github.com/tensorflow/java-models/blob/master/tensorflow-examples/src/main/java/org/tensorflow/model/examples/mnist/CnnMnist.java

We're working on building out Java implementations of the ops written in Python but there are a lot and it's not finished yet. If you've built a model using those...

[DeepFM](https://arxiv.org/abs/1703.04247) should be implementable entirely within TF-Java without using any of those operations, it's just a pairwise feature interaction using an embedding vector and an MLP. Is there a specific...

In many cases (e.g. tensorflow-text) you can load the native library that contains the ops with `TensorFlow.loadLibrary(String)`. That should allow `SavedModelBundle` to load models that contain those ops. I've not...

As you've found this seems to be an issue with how TF-DF defines its operations (https://discuss.tensorflow.org/t/decision-forests-issue-with-c-api/7434/5), and is outside our control. Until they fix the op definition I don't think...

I expect so. I don't think it's actually going to do anything with the inferred shape as I doubt there are many operations dowstream of it, but the C API...

As we pass in variables by name when functions are called then having something without a name is going to break if you skip the validation (unless you don't use...

What's your `$JAVA_HOME` set to?

Maven pulls java from `JAVA_HOME` not the `java` it finds on your path, so it's using Java 8 to compile it and our minimum is 11. If you set your...

Don't try and compile TF-Java using Rosetta, you'll pull in a TF binary which has AVX instructions which will cause a SIGILL and take down the JVM. I've not tried...