tensorflow / tensorflow/tflite-support

broken model after adding metadata

Open
#1,011 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
C++
Stars
441
Forks
146
PR merge metrics
No merged PRs in 30d

Description

Good day! I'm new to this, so forgive the stupid question. I'm trying to run MobileClip2_S0 via MediaPipe and Android ImageEmbedder Tasks, which requires model metadata to run. I successfully converted the model to Litert (Tflite) format, but after adding the metadata, the PlaceholderForGreaterOpCodes placeholders appear in the model. What should I do? Thanks!

1 img - model ok
Image

2 img - broken
Image

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reviewing the reported conversion from MobileClip2_S0 to LiteRT (TFLite) and the subsequent metadata addition for MediaPipe Android ImageEmbedder Tasks. Compare the two attached model states and determine why PlaceholderForGreaterOpCodes appears after metadata is added; done means documenting a reproducible cause and the required compatible conversion or metadata process.

Written by the indexing model from the issue text.

Assessment

Tech stack
android
Domain
machine-learning, mobile-dev
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
28/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.