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.

Sign up for GitHub

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

Jump to bottom

Discrepancy in Model Performance Compared to Example #60

Open
cesarpgouveia opened this issue Aug 8, 2023 · 0 comments
Open

Discrepancy in Model Performance Compared to Example #60

cesarpgouveia opened this issue Aug 8, 2023 · 0 comments

Comments

@cesarpgouveia
Copy link

cesarpgouveia commented Aug 8, 2023 •
edited
Loading

Environment

  • TensorflowLite
  • Ubuntu 22.04

Issue Details

I've been using the example code provided in the repository (https://github.com/iwatake2222/play_with_tflite/tree/master/pj_tflite_face_landmark_with_attention) to work with the face mesh with attention model. However, I've noticed a significant difference in performance compared to the results shared in another example I found online (https://storage.googleapis.com/tfjs-models/demos/face-landmarks-detection/index.html?model=mediapipe_face_mesh). I am running the code from a virtual machine with Ubuntu 22.04. I followed the steps to set up TensorFlow Lite and haven't made any changes to the test script (main.cpp). Below are two images that illustrate the difference in performance between models.

Capture4

image

Just wanted to drop a line to say a big thanks in advance to anyone who can help out with this.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@cesarpgouveia