PaddlePaddle VS onnx

Click to Learn more...

PaddlePaddle?

https://github.com/PaddlePaddle/Paddle

Also, Baidu have quite a few OSS projects out there in general.

https://github.com/baidu

Volcano is a batch scheduler on top of Kube-batch targetting spark-operator, plain old MPI, chinesium paddlepaddle, and Kromwell HPC.

Once your model has been trained and validated using Anomalib, the next step is to prepare it for real-time implementation. This is where ONNX (Open Neural Network Exchange) or OpenVINO (Open Visual Inference and Neural network Optimization) comes into play.

ONNX is an open format from the Linux Foundation to represent machine learning models. It is becoming extensively adopted by the Machine Learning community and is compatible with most of the machine learning frameworks like PyTorch, TensorFlow, etc. Converting a model between any of those formats and ONNX is really simple and can be done in most cases with a single command.

ONNX[0], model-as-protosbufs, continuing to gain adoption will hopefully solve this issue.

[0] https://github.com/onnx/onnx

ONNX is a format for representing machine learning models in a portable way. Additionally, ONNX models can be easily optimized and thus become smaller and faster.

I would say onnx.ai [0] provides more information about ONNX for those who aren’t working with ML/DL.

[0] https://onnx.ai

This kind of indirection through standardisation is pretty common to make compatibility between different kinds of software components easier. Some other good examples are the LSP project from Microsoft and ONNX to represent machine learning models. The first provides a standard so that IDEs don't have to re-invent the weel for every programming language. The latter decouples training frameworks from inference frameworks. Going back to WSGI, you can find a pretty extensive rationale for the WSGI standard here if interested.

Sounds interesting, ONNX runtime - what I use - can also be run with WebAssembly and on CPU, on all major GPUs, and it supports many programming languages, though C++ is its direct form.

No, it's that AMD doesn't fucking need to. If anything, it the owners of ONNX that needs to convince developers that their technology is worth learning and using it to implement solutions, whether it's on laptops or phones or Raspberry Fucking Pi.