Chin-Chang Yang

Does this change upgrade all python scripts to run with tensorflow 2.4? I also need to upgrade python scripts to run with tensorflow 2.9 because it is the only version...

That's OK. I found a method to convert a TensorFlow 1.x network to Apple's Core ML model on Google Colab, so I don't have a strong requirement to upgrade to...

I tested katago on Apple M1 Pro: ``` % cpp/katago version KataGo v1.11.0 Git revision: 714ad713a829e2fca465ec4113bb1afa4c6ec543 Compile Time: Jul 31 2022 11:35:36 Using OpenCL backend ``` I got visits/s =...

> Which Apple M1 Pro box? > > score [1000102](tel:1000102) seems high, or even out of range? It is [Macbook Pro](https://www.apple.com/macbook-pro-14-and-16/) with M1 Pro chip.

It has been a long time until now. Does this change pass any test cases in the most recent katago?

There is no [CoreML](https://developer.apple.com/documentation/coreml) GPU backend. Do you actually want to say [Metal](https://developer.apple.com/documentation/metalperformanceshaders/)?

I think there are two possible ways to improve katago performance on MacOS. The first way is straightforward. Create backend functions with low-level primitives like Accelerate and [BNNS](https://developer.apple.com/documentation/accelerate/bnns?language=objc), as well...

A quick update here. The first way might not utilize Apple Neural Engine (ANE), so its performance could not be best. The second way utilizes ANE if the model configuration...

I have written an article to describe KataGo CoreML backend on my [page](https://chinchangyang.github.io/github/katago/coreml/apple/m1/arm64/2022/08/20/run-katago-with-opencl-coreml.html). My test results show that CoreML does not use much GPU. In fact, I see 0% GPU...

> @ChinChangYang Would you please commit the `KataGoModel.mlpackage` file into [your branch](https://github.com/ChinChangYang/KataGo/tree/coreml-backend)? I uploaded `KataGoModel.mlpackage` to my [release](https://github.com/ChinChangYang/KataGo/releases/tag/v1.11.0-coreml1) page.