huggingface / huggingface/candle
Demo showing how to load in candle computer vision model using webcam
- Dominant language
- Rust
- Stars
- 21k
- Forks
- 1.8k
- Avg merge
- 16h 42m
- Merged PRs (30d)
- 25
Description
```
use anyhow::Result; // Automatically handle the error types
use opencv::{
prelude::*,
videoio,
highgui
}; // Note, the namespace of OpenCV is changed (to better or worse). It is no longer one enormous.
fn main() -> Result<()> { // Note, this is anyhow::Result
// Open a GUI window
highgui::named_window("window", highgui::WINDOW_FULLSCREEN)?;
// Open the web-camera (assuming you have one)
let mut cam = videoio::VideoCapture::new(0, videoio::CAP_ANY)?;
let mut frame = Mat::default(); // This array will store the web-cam data
// Read the camera
// and display in the window
loop {
cam.read(&mut frame)?;
highgui::imshow("window", &frame)?;
let key = highgui::wait_key(1)?;
if key == 113 { // quit with q
break;
}
}
Ok(())
}
```
Here is a basic example of opening Qt using Opencv-rust.
It would be great to have a working example using this alongside candle!
Open to submitting this as a pr in any of the example folders.
Contributor guide
No contributing guide indexed for this repository
Research direction
Start by reviewing the existing example folders and the provided opencv-rust webcam snippet. Determine how a Candle computer vision model should be loaded alongside webcam capture and display. Done means a working example in an example folder that combines Candle with OpenCV webcam input.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- opencv, rust
- Domain
- computer-vision
- Issue type
- Feature
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 38/100