tensorflow / tensorflow/model-optimization
Disable quantization range during training
Open
@Xhark is already working on this.
Since Aug 9, 2021.
- Dominant language
- Python
- Stars
- 1.6k
- Forks
- 349
- Avg merge
- 3d 2h
- Merged PRs (30d)
- 1
Description
Hi,
As the paper (https://arxiv.org/pdf/1712.05877.pdf) refereed by Tensforflow states:
"we found it useful to completely disable activation quantization at the start of training (say, for 50 thousand to 2 million steps). This allows the network to enter a more stable state where activation quantization ranges do not exclude a significant fraction of values."
I would like to disable activation during the first iterations, Is there a way to do it in Tensorflow?
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.
Assessment
This issue has not been assessed yet.