onnxruntime VS netron

ONNX Runtime: ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

Embedding generation uses the ONNX runtime under the hood. This is a cross-platform inferencing library that supports multiple execution providers from CPU to specialized GPUs.

tfjs is dead, looking at the commit history. The standard now is to convert PyTorch to onnx, then use onnxruntime (https://github.com/microsoft/onnxruntime/tree/main/js/web) to run the model on the browsdr.

- slang[2] has the potential, but the meta programming part is not as strong as C++, existing libraries cannot be used.

The above conclusion is drawn from my work https://github.com/microsoft/onnxruntime/tree/dev/opencl, purely nightmare to work with thoes drivers and jit compilers. Hopefully Vcc can take compute shader more seriously.

[1]: https://www.circle-lang.org/

I did. It depends what you want, for an overview of how ONNX Runtime works then Microsoft have a bunch of things on https://onnxruntime.ai, but the Java content is a bit lacking on there as I've not had time to write much. Eventually I'll probably write something similar to the C# SD tutorial they have on there but for the Java API.

For writing ONNX models from Java we added an ONNX export system to Tribuo in 2022 which can be used by anything on the JVM to export ONNX models in an easier way than writing a protobuf directly. Tribuo doesn't have full coverage of the ONNX spec, but we're happy to accept PRs to expand it, otherwise it'll fill out as we need it.

What about models besides GPT? Most of the popular vector encoding models aren't using this architecture.

If you really didn't want PyTorch/Transformers, you could consider exporting your models to ONNX (https://github.com/microsoft/onnxruntime).

In exploring open-source projects, I've come across several promising tools capable of managing deep-learning models for images. Significantly, tools such as NETRON provide visualization of neural networks, while SHAP can be used for evaluating the significance of outputs.

We need to find out the exact input and output tensor names. A tool like Netron makes this super easy. Open the original .tflite and/or the ONNX model in Netron and click the Model Properties button in the lower left corner.

How is this different from e.g Netron https://github.com/lutzroeder/netron

Netron (https://netron.app/) is the best and mostly used NN visualizer. Just save your model and then simply load it via netron to look its layers and weights. If you want a more complex visualization then you can also play with Zetane ( but its paid, also have a free version) engine.