mediapipe
mediapipe copied to clipboard
googlesamples
Hello, I am playing around with your Face Landmarker app for android. I am very inexperienced with Koltin, so my apologies. I would like to display only certain landmarks on...
In this documentation https://developers.google.com/mediapipe/solutions/vision/pose_landmarker/android , It is given that the result will be this: PoseLandmarkerResult: Landmarks: Landmark #0: x : 0.638852 y : 0.671197 z : 0.129959 visibility : 0.9999997615814209...
there is no face found if I used full body picture. here is my test code https://colab.research.google.com/drive/1iXrX4P1ft-MQ4uBThM5Ux8w5uZAlbkYZ?usp=sharing
Both `com/google/mediapipe/tasks/genai/llminference/LlmInference#generateResponse` and `com/google/mediapipe/tasks/genai/llminference/LlmInference#generateResponseAsync` methods freeze the Main Thread if the prompt provided is very long (1000 Tokens). Wrapping the call in a async thread doesn't seem to work: ```...
When you try to select a video that is longer than 10 seconds, it keeps loading forever. I checked the code, and basically it takes the video, obtain all the...
Dear @PaulTR Again, thanks for the awesome work! In our project we only need 12 (main body joints) out of the 33 inferred landmarks. Would a model predicting only 1/3...
Running the standard colab get No module named 'keras.src.engine' 
hello, when i run object_detection demo, i get this error: Object detector failed to load model with error: internal: ; RET_CHECK failure (mediapipe/util/resource_util_android.cc:86) last_slash_idx != std::string::nposefficientdet-lite0.tflite doesn't have a slash...
@PaulTR Great project, I can already run it on my phone, but I have some questions, I want to understand the whole process of running pipline 1. Is unet batch=2...
Can I simply change the model to ’Pose landmarker (Full)‘ on the Face Detection‘s demo and implement it?
