-
### Have I written custom code (as opposed to using a stock example script provided in MediaPipe)
No
### OS Platform and Distribution
Android
### MediaPipe Tasks SDK version
_No response_
### Ta…
-
Hi, could you please tell me that how do you get procrustes_landmark_basis? How do you choose the points of landmark and how to set weight of each points？If I add more points or adjust weights,could i…
-
Hi. I need this code to be running on windows.
Would you kindly advise me how I can build on windows ?
Thanks.
-
Hello, This is not an issue I need some help from you with the following scenario :
I have to work on a Human Pose Estimation project using OpenCV and MediaPipe in Unity. In that, I need to track m…
-
之前写原生app的时候调用了mediapipe的face landmarks模型，性能可以稳定在60fps。目前小程序运行face landmarks的performance在15-20fps之间，请问还有可能继续提升吗？有什么更好的提升方法吗？理论上来说，Face landmarks的模型应该是非常性能了哈哈哈
-
Followed this "recipe" for building on Raspberry Pi, but I was trying on Pi 3b+ and I am using bazel from "bazel-bin" and I get the undeclared symbol error. I've tried varying some of the opencv BUIL…
-
Hi
just a heads up for a similar project (https://github.com/floe/backscrub) which has implemented the Google Meet Segmentation Model for tensorflow - I can actually achieve 25+ Frames on a normal…
-
### OS Platform and Distribution
Windows 11
### Compiler version
Visual Studio 2019
### Programming Language and version
C++
### Installed using virtualenv? pip? Conda?(if python)
…
-
Hi,
Is it possible to retrain the model with custom dataset.
-
After I run "start" script I've got the error:
**_No module named 'PIL'_**
I can easily run python shell and import that module like "import PIL" and it's ok, but the script doesn't see that mod…