-
Hello!
Thank you for publishing your wonderful code!
I am a student in Japan and would like to use your research for my own study!
However, I am having trouble finding a solution to the error I…
ghost updated
6 months ago
-
Hi, do you have any idea to translate your logic into opengl es ( for porting your work into android)
I understand that your logic contains of 4 main parts
1. Extract landmarks from src image
2.…
-
感谢楼主分享哈^_^
尝试把代码合到darknet最新版本，发现这里的循环又用到了i
https://github.com/ouyanghuiyu/darknet_face_with_landmark/blob/2db381ee665fd16ae0dda62749e5411523371e97/src/yolo_layer.c#L724
-
I don't know if you have done some operation to make your models have the same output as offcial models
-
Awesome repo! I'm having an issue with the project, however, when rotating my device to either Landscape Left or Landscape Right orientation. I've chosen to allow all orientations in the sample app,…
-
Can I use infrared images as input? @liguohao96
-
Hi,
When I use GPU to do face detection, I found that the memory used of the GPU keep increasing. Maybe there is an memory leak issue.
The detector I used as flowing:
mtcnn_detector = MtcnnDetect…
-
### Have I written custom code (as opposed to using a stock example script provided in MediaPipe)
Yes
### OS Platform and Distribution
Ubuntu 22.04.4 LTS
### Mobile device if the issue happens on …
-
in code you use canonical_face_model.obj(mediapipe defined), if i want to use my custom face mesh, how to do it by mediapipe, thank you
-
我用RetinaFace（包括在你的框架下构建的其他检测器）在不带landmark自己的数据集上训练的模型（训练size 512 x 512），发现512的测试size会发生严重的检测框偏移（都是向左下），原图测试无偏移且结果正常。但带landmark的WIDER FACE数据集训练的模型基本没有偏移，而且做landmark和不做landmark的相同检测器均存在偏移。
请问下我是哪个环节出错了…