tensorflow / tensorflow/tflite-support
Manually setting ranges for every activation and weight
Nobody has claimed this yet.
- Dominant language
- C++
- Stars
- 441
- Forks
- 146
- PR merge metrics
- No merged PRs in 30d
Description
Hello Team, is it posibble to set the scale and offset of all the activations and weights manually, rather than going with tflite quantization schemes? Actually I want to run tflite inference through ranges using AIMET quantization scheme. They output a json formatted file containing ranges for every weights and activations, I want to use those ranges to create tfite quantized model, for testing purposes
Contributor guide
No contributing guide indexed for this repository
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
The issue names no files, tests, or entry points. Start by locating the TFLite quantization or model-conversion entry point and reviewing how activation and weight ranges are represented. Done would require a clearly defined way to use AIMET's JSON ranges when creating a quantized TFLite model, with coverage for the requested behavior.
Written by the indexing model from the issue text.
Assessment
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 22/100