tensorflow / tensorflow/recommenders
[Question] Input for Tflite from Basic Retrieval Model
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 2k
- Forks
- 300
- PR merge metrics
- No merged PRs in 30d
Description
_, titles = index(tf.constant(["42"]))
print(f"Recommendations for user 42: {titles[0, :3]}")
Based on the script above, the input for the recommendation is a string type ("42") but the string cannot be used for tflite input. how do i use this model from basic retrieval in android ?
Or is there a way to deploy the model from basic retrieval to android?
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with the Basic Retrieval Model example shown in the issue and review how its string input is exposed to TensorFlow Lite and Android. Done would require a documented, supported path for using or deploying this model from Android, including the expected input representation.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- android, python, tensorflow
- Domain
- machine-learning, mobile-dev
- Issue type
- Documentation
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100