Rob Wilkinson

I have just compiled jhead 3.08 on my MacM2 - Ventura. Everything ran cleanly but with a warnining, and based on my simple tests, successfully. The warning information may be...

Thank you for that. I'm naive about modern compilers and had never heard of address sanitisation or asan. My C days are over 40 years behind me! Very useful to...

pyiqa runs on my Apple Silicon M2, Sonoma. I've only run the hyperiqa metric on 2 images and got results more or less in line with my own judgement. If...

I attach two files recording the results of my tests of pyIQA on Apple Silicon running Sonoma I used the Warp terminal which is rather smart and helpful. (https://www.warp.dev/) I've...

Done Terminal efficiency report attached. Also, for completeness a CPU run of test_cal FYI Have you spotted this paper and code posted 2 weeks ago: LAR-IQA: A Lightweight, Accurate, and...

Herewith. Regards Rob ***@***.***  > On 18 Sep 2024, at 16:46, Chaofeng Chen ***@***.***> wrote: > > > Thank you for your help! Could you please attach the results...

This time? [calibration_summary.csv](https://github.com/user-attachments/files/17071069/calibration_summary.csv)

No problem: [Efficiency_benchmark.csv](https://github.com/user-attachments/files/17071177/Efficiency_benchmark.csv)

I've been looking at: https://pytorch.org/tutorials/intermediate/torch_compile_tutorial.html Are there any bottleneck points you can pinpoint that would benefit from using torch.compile? If yes I'd be interested to test them for you.

Thanks for your explanation. On Fri, 20 Sep 2024 at 19:32, Chaofeng Chen ***@***.***> wrote: > Thank you for your suggestions. It is indeed possible to further > accelerate certain...