update doc of yunet with specification of detectable face sizes (#118)
Browse files
models/face_detection_yunet/README.md
CHANGED
@@ -5,6 +5,7 @@ YuNet is a light-weight, fast and accurate face detection model, which achieves
|
|
5 |
Notes:
|
6 |
|
7 |
- Model source: [here](https://github.com/ShiqiYu/libfacedetection.train/blob/a61a428929148171b488f024b5d6774f93cdbc13/tasks/task1/onnx/yunet.onnx).
|
|
|
8 |
- For details on training this model, please visit https://github.com/ShiqiYu/libfacedetection.train.
|
9 |
- This ONNX model has fixed input shape, but OpenCV DNN infers on the exact shape of input image. See https://github.com/opencv/opencv_zoo/issues/44 for more information.
|
10 |
|
|
|
5 |
Notes:
|
6 |
|
7 |
- Model source: [here](https://github.com/ShiqiYu/libfacedetection.train/blob/a61a428929148171b488f024b5d6774f93cdbc13/tasks/task1/onnx/yunet.onnx).
|
8 |
+
- This model can detect **faces of pixels between around 10x10 to 300x300** due to the training scheme.
|
9 |
- For details on training this model, please visit https://github.com/ShiqiYu/libfacedetection.train.
|
10 |
- This ONNX model has fixed input shape, but OpenCV DNN infers on the exact shape of input image. See https://github.com/opencv/opencv_zoo/issues/44 for more information.
|
11 |
|