depthai
depthai copied to clipboard
DepthAI Python API utilities, examples, and tutorials.
Oak D Lite is a powerful camera with 4k capabilities. What it can do wonderful stuff with AI recognition in 4K or HD resolution, it can outclass other usual webcam...
**Describe the bug** Running `python3 demo_script.py --app uvc` with OAK-D-Lite creates /dev/video* device(s) only for a few seconds, the camera then disconnects and reconnects again as a non-uvc device, the...
**Check if issue already exists** I couldn't find anything that sounds similar. **Describe the bug** Creating an `ImageManip` node and calling both `setRotationDegrees` and `setResizeThumbnail` causes the pipeline to fail...
I am building a point cloud with the Oak-D Lite using the ppx and ppy found in the getCameraIntrinsics. I have substituted approximate values for fx and fy because I...
### Start with the `why`: The tiny variant of [YOLOX](https://github.com/Megvii-BaseDetection/YOLOX) has a number of advantages over yolov4-tiny: - [Significantly higher AP](https://arxiv.org/pdf/2107.08430.pdf): **33% v.s. 22%**! - It's Anchorless - It's slightly...
**Description of the bug** Running the DepthAI demo with `python3 depthai_demo.py` using a USB-C OAK-D in an LXD container fails to find the device after booting. Instead it gives the...
**Describe the bug** Use the `main` branch to calibrate the OV9782 global shutter RGB camera failed. I know that the `ov9782_color` branch can be used, but the output depth and...
**Describe the bug** While running extended tests of the same TinyYOLOV4 script, the OAK-D-POE aborted with an X_LINK_ERROR after 7 hours, and the OAK-D-IOT (connected via USB to host) aborted...
I'm trying to deploy YOLOX on an Oak device. I can load the model but I don't know how extract the output of the model. I downloaded the YOLOX Nano...
**Describe the bug** When running the same TinyYOLOV4 detection model, The OAK-D-PoE shows the LeonOS CPU load as 90-93% while the OAK-D and OAK-D-LITE show a LenoOS CPU load of...