FakeQuantizeWithMinMaxVars support
Open
Nobody has claimed this yet.
good first issue
- Dominant language
- C++
- Stars
- 333
- Forks
- 150
- Avg merge
- 4d 19h
- Merged PRs (30d)
- 54
Description
The standard way to implement "fake quantization" in TF is the FakeQuantizeWithMinAndMaxVars operator, which we don't support. We support the ONNX way of doing this is QuantizeLinear and DequntizeLinear ops. Let's support it!
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
Start by locating the existing QuantizeLinear and DequantizeLinear operator support, then compare it with the TensorFlow FakeQuantizeWithMinAndMaxVars operator described here. Determine the relevant implementation and test entry points, and consider the work complete when graphs using this operator are supported and covered by tests.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp, tensorflow
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100