Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Can not use GPU on kaggle notebook. #5871

Open
459zyt opened this issue Feb 28, 2025 · 2 comments
Open

Can not use GPU on kaggle notebook. #5871

459zyt opened this issue Feb 28, 2025 · 2 comments
Assignees
Labels
gpu MediaPipe GPU related issues platform:python MediaPipe Python issues stale stat:awaiting response Waiting for user response task:face landmarker Issues related to Face Landmarker: Identify facial features for visual effects and avatars. type:feature Enhancement in the New Functionality or Request for a New Solution

Comments

@459zyt
Copy link

459zyt commented Feb 28, 2025

MediaPipe Solution (you are using)

Face landmark detection

Programming language

python

I set use GPU on kaggle, but it raises error.

###My code

base_options = python.BaseOptions(
    
model_asset_path='/kaggle/input/face_landmarker.task/other/default/1/face_landmarker.task',
delegate=python.BaseOptions.Delegate.GPU
)

options = vision.FaceLandmarkerOptions(base_options=base_options,
                                       output_face_blendshapes=True,
                                       output_facial_transformation_matrixes=True,
                                       num_faces=1)
detector = vision.FaceLandmarker.create_from_options(options)

error

err :---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last) in <cell line: 47>() 45 output_facial_transformation_matrixes=True, 46 num_faces=1) ---> 47 detector = vision.FaceLandmarker.create_from_options(options) 48 49 /usr/local/lib/python3.10/dist-packages/mediapipe/tasks/python/vision/face_landmarker.py in create_from_options(cls, options) 3102 task_options=options, 3103 ) -> 3104 return cls( 3105 task_info.generate_graph_config( 3106 enable_flow_limiting=options.running_mode /usr/local/lib/python3.10/dist-packages/mediapipe/tasks/python/vision/core/base_vision_task_api.py in init(self, graph_config, running_mode, packet_callback) 68 'callback should not be provided.' 69 ) ---> 70 self._runner = _TaskRunner.create(graph_config, packet_callback) 71 self._running_mode = running_mode 72 RuntimeError: Service "kGpuService", required by node mediapipe_tasks_vision_face_landmarker_facelandmarkergraph__mediapipe_tasks_vision_face_detector_facedetectorgraph__mediapipe_tasks_core_inferencesubgraph__inferencecalculator__mediapipe_tasks_vision_face_landmarker_facelandmarkergraph__mediapipe_tasks_vision_face_detector_facedetectorgraph__mediapipe_tasks_core_inferencesubgraph__InferenceCalculator, was not provided and cannot be created: ; RET_CHECK failure (mediapipe/gpu/gl_context_egl.cc:84) egl_initializedUnable to initialize EGL

@459zyt 459zyt added the type:feature Enhancement in the New Functionality or Request for a New Solution label Feb 28, 2025
@kuaashish kuaashish assigned kuaashish and unassigned kalyan2789g Mar 3, 2025
@kuaashish kuaashish added platform:python MediaPipe Python issues gpu MediaPipe GPU related issues task:face landmarker Issues related to Face Landmarker: Identify facial features for visual effects and avatars. labels Mar 3, 2025
@kuaashish
Copy link
Collaborator

Hi @459zyt,

To better understand the issue, please share the complete system details, specifically: the Operating System and its version, the MediaPipe version, and the Python version. A template is available for your convenience. This information will enable us to reproduce the issue, if necessary, and provide a status update.

Thank you!!

@kuaashish kuaashish added the stat:awaiting response Waiting for user response label Mar 3, 2025
Copy link

This issue has been marked stale because it has no recent activity since 7 days. It will be closed if no further activity occurs. Thank you.

@github-actions github-actions bot added the stale label Mar 11, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
gpu MediaPipe GPU related issues platform:python MediaPipe Python issues stale stat:awaiting response Waiting for user response task:face landmarker Issues related to Face Landmarker: Identify facial features for visual effects and avatars. type:feature Enhancement in the New Functionality or Request for a New Solution
Projects
None yet
Development

No branches or pull requests

3 participants