-
Notifications
You must be signed in to change notification settings - Fork 5k
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
Object detection model can't be used in C++ #5389
Comments
#5308 more details in this issue I raised 1 month ago |
Have you tried the model in MediaPipe Studio? https://mediapipe-studio.webapps.google.com/studio/demo/object_detector |
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. |
This issue was closed due to lack of activity after being marked stale for past 7 days. |
@schmidt-sebastian the model in MediaPipe Studio is EfficientDet-lite0, the model in model maker are |
In "mediapipe/graphs/object_detection/object_detection_desktop_live.pbtxt" , I repalece "ssdlite_object_detection.tflite" with "efficientdet_lite0.tflite", error appeared: "Check failed: raw_box_tensor->dims->data[1] == num_boxes_ (19206 vs. 2034)", I think it is the difference between of model structure, so the postprocess is also different. In a word, in the C++ desktop example, we can't just repalece the object detection model with efficientdet model and mobilenet, so I think model maker about object detection is not useful in C++ example. |
Have I written custom code (as opposed to using a stock example script provided in MediaPipe)
None
OS Platform and Distribution
ubuntu20
Python Version
3.11
MediaPipe Model Maker version
0.2.1.3
Task name (e.g. Image classification, Gesture recognition etc.)
Object detection
Describe the actual behavior
model maker train is successful, but failed in C++ inference
Describe the expected behaviour
the trained model can inference in C++
Standalone code/steps you may have used to try to get what you need
Other info / Complete Logs
No response
The text was updated successfully, but these errors were encountered: