-
Hello, thanks for your awesome work.
I'm having trouble on running tracker.py.
def parse_batch(self, batch):
images = batch['image']
landmarks = batch['lmk']
landmarks_dense = bat…
-
### Have I written custom code (as opposed to using a stock example script provided in MediaPipe)
None
### OS Platform and Distribution
windows
### MediaPipe version
10.00
### Bazel version
6.4…
-
Hello,
Do the tensorflow face landmarks detection and Iris landmarks models work on Infrared/grayscal image/video? I have a camera which captures Infrared streams, can I run this model over the inf…
-
I referenced the source code of [FaceBlendShapesGraph](https://github.com/google/mediapipe/blob/master/mediapipe/tasks/cc/vision/face_landmarker/face_blendshapes_graph.cc) and put it into a "legacy" s…
-
i know there are already Issues about this [9](https://github.com/KeyuWu-CS/MonoHair/issues/9)and[15](https://github.com/KeyuWu-CS/MonoHair/issues/15),But the question seem still exist when run on myd…
-
Hello, thank you very much for sharing, I had the following while reproducing with the gaze360 dataset, I thought that the example_images had too few images, so I used a class from WIDER to get the pk…
-
Error occurred when executing MediaPipe-FaceMeshPreprocessor:
Failed to parse: node {
calculator: "ImagePropertiesCalculator"
input_stream: "IMAGE:image"
output_stream: "SIZE:image_size"
}
nod…
-
At present `iris.py` [first uses `FaceMesh`](https://github.com/Rassibassi/mediapipeDemos/blob/47c6330227c88ca02e32deb47b150aa8391306a4/iris.py#L47-L55) to find the eyes and then uses another model to…
-
Hi,
I did some qualitative assessment using my own data trying to test `face alignment + headpose + gaze`. I merged some code from this repository and some additional code from lazer eye as you ref…
-
Thanks for your greate work.
The result you showed in README has irises. But I found `faces` list in demo.py is 468 landmarks. How can I get 478 points with irises?