ultralytics VS hyperfine

Yep, I noticed this a while ago. It posts easily identifiable ChatGPT responses. It also posts garbage wrong answers which makes it worse than useless. Totally disrespectful to the userbase.

https://github.com/ultralytics/ultralytics/issues/5748#issue...

There are obvious places it is being used that I have noticed organically. For instance, check out the answers in this repo:

https://github.com/ultralytics/ultralytics/issues/5748#issue...

If you read the answers there, the style of answering is always to repeat the question in a very specific way. Once you see it you can’t in-see it.

When browsing the state-of-the-art in object detection on Papers with Code, I found the YOLO model to be one of the most popular, accurate, and fastest. That being said, I would recommend having a look at Ultralytics, which provides the tools to evaluate, predict, and export the latest versions of YOLO models with only a few lines of code.

YOLOv8 (You Only Look Once) is an open-source Computer Vision AI model released on January 10th, 2023. It’s called YOLO because it detects everything inside an image in a single pass. The new version can perform image detection, classification, instance segmentation, tracking, and pose estimation tasks.

Next, I needed to figure out, how can I access the stream, recognize an animal, then let Max know? There are tons of examples of recognizing an object via camera frames, but I ultimately found this python library called ultralytics that supports RTSP streams and classifying objects in the video frames using pre-built models. The docs looked like it would be pretty low effort, so after some experimentation, I was successful in having the ultralytics library recognize objects from my cheap camera!

I have created an issue in their Github as well but so far not much help has been recieved. You can check that here

And the target models include: * YOLOv8 (You Only Look Once) * YOLO-NAS * YOLOv5 * and DETR

Check out the official hyperfine Github repo

And then I used hyperfine to run the benchmarks on my MacBook Pro 14 M2 Max, and here are the results:

Search "benchmarking tools for linux" and decide that hyperfine is good for what I'm doing. Run Jennifer's new python script against my refactored perl and find that the python is 1.26 times faster for k=3 and 1.47 times faster for k=4. For the Covid-19 sequence, these are both on the order of hundreds of milliseconds.

> It is very possible to write sub 100ms procedures in TS, […]

I will not disagree with this statement because I don’t have a way to test inshellisense right now. Could you (or anyone with a working Node + NPM installation) please install inshellisense and post the actual numbers? Perhaps using a tool like hyperfine (https://github.com/sharkdp/hyperfine).

Yeah, while it's not as thorough as these tools, the method is at least reproducible and sane, and with ~10 or so samples, you get an interval with a nice confidence.

Another through method will be hyperfine[0], yet I wanted to provide a method which requires no installation and can be done in a whim, without jumps and hoops, with the tools already at hand.

[0]: https://github.com/sharkdp/hyperfine

That is native and inbuild but I would suggest below options instead 1. Using lazy's Profile tab instead https://github.com/folke/lazy.nvim 2. Using a dedicated plugin to do this https://github.com/dstein64/vim-startuptime. 3. Using an external program hyperfine is one that I use https://github.com/sharkdp/hyperfine

Fair enough, although might I recommend using hyperfine for your testing? ;p