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

YOLO: create and publish a tflite model on TF Hub #1

Open
margaretmz opened this issue Jul 17, 2020 · 2 comments
Open

YOLO: create and publish a tflite model on TF Hub #1

margaretmz opened this issue Jul 17, 2020 · 2 comments
Projects
E2E TFLite Tutorials Project Board

Comments

@margaretmz
Copy link
Contributor

No description provided.

@margaretmz margaretmz created this issue from a note in E2E TFLite Tutorials Project Board (In progress) Jul 17, 2020
@khanhlvg
Copy link

khanhlvg commented Jul 20, 2020 •
edited

@hunglc007 who created this repo is working on converting YOLOv3_tiny to TF Lite. So far he has succeeded on creating a YOLOv3_tiny model that can run on TF Lite GPU.

The model training part is still needed to be done in darknet. Hung is working on implementing a training pipeline on TF2.

@sayakpaul
Copy link
Contributor

@hunglc007 could you provide an update on this project?

If you were able to obtain a TFLite variant of YOLOv3_tiny could you help me with the following?

  • Notebook that shows the conversion process and inference in Python
  • Links to the TFLite models

Additionally, would you be interested in publishing these models from TensorFlow Hub? That way the models could reach an even bigger audience.

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
E2E TFLite Tutorials Project Board
  
In progress
Milestone
No milestone
Development

No branches or pull requests
3 participants
@margaretmz @khanhlvg @sayakpaul