tensorflow / tensorflow/model-optimization
Set zero_debias=True for Quantization Aware Training
Open
@Xhark is already working on this.
Since Oct 12, 2021.
- Dominant language
- Python
- Stars
- 1.6k
- Forks
- 349
- Avg merge
- 3d 2h
- Merged PRs (30d)
- 1
Description
Hi,
I see that TF version 1's QAT library uses zero_debias as True. However, the TFMOT's quantization library calls the following in the quant_ops.py:
assign_min = moving_averages.assign_moving_average(
min_var, range_min, ema_decay, zero_debias=False, name='AssignMinEma')
assign_max = moving_averages.assign_moving_average(
max_var, range_max, ema_decay, zero_debias=False, name='AssignMaxEma')
When I set the zero_debias to be True, I hit this error:
Tensor.op is meaningless when eager execution is enabled.
Do you have plans in the future to support zero_debias=True for QAT ?
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.