MaixPy icon indicating copy to clipboard operation
MaixPy copied to clipboard

Easily create AI projects with Python on edge device

Results 26 MaixPy issues
Sort by recently updated
recently updated
newest added

![Image](https://github.com/user-attachments/assets/b3c441bb-1f5a-48a0-a800-774b0cbdd6a4) ![Image](https://github.com/user-attachments/assets/621b8edb-771c-4494-b98f-c148f2d483ac)

documentation

![Image](https://github.com/user-attachments/assets/39c25cc5-8705-43b0-82e6-501ddbc81fc5) 看了API文档里面没有可以设置的 ![Image](https://github.com/user-attachments/assets/44914163-e7ad-4c22-b32e-f25a019abf71)

enhancement

![Image](https://github.com/user-attachments/assets/636d3400-e601-4d2e-8712-6e538a5a18f3) 想要修改已经学习过的人脸的 label

enhancement

以下代码会报错,预期结果应该是要正确运行 ``` detector = nn.YOLO11(model="/root/models/yolo11n.mud", dual_buff=True) cam = camera.Camera(disp.width(), disp.height(), image.Format.FMT_RGBA8888) ```

usage

由于我打算借助maixpy的image对象来创建一个图片,并显示到oled显示屏上,所以尝试了一下创建128*32的图像,发现显示异常,但时比这个高度小或者高度高于54的话,显示正常,只有当宽度为128且高度为32~52时才会显示异常,期望可以修复此问题。 似乎只有灰度Format的image才有此问题? ![Image](https://github.com/user-attachments/assets/ff3e4154-8abe-4791-b667-b51dfa23aad3) ``` from maix import image, app, display, time disp = display.Display() width, height = 128, 54 img = image.Image(width, height, image.Format.FMT_GRAYSCALE) img.draw_rect(1, 1, width - 2, height...

text OCR can add whitelist or limit char in my case only eng and number

usage

![Image](https://github.com/user-attachments/assets/542d219f-7672-4b22-991c-8c6f133e47be) ![Image](https://github.com/user-attachments/assets/0a5e40c0-e1fe-4bc5-b82e-361f8027d020) 我给它识别的图片是带风岔路口的,但get_regression返回的lines每次都是1个

Hi, I tried to run custom model and it run very slow, compared to YOLO. I tested with `examples/vision/ai_vision/nn_forward.py` and my model had forward time ~280ms compared to 11ms for...