Hacktoberfest 2026：维护者为十月标记出来的 issue，仍然开放、适合新手。 浏览 Hacktoberfest issue

strange behavior when quantizing a model.

未关闭
  • 哪里不对？
#1,109 2 条评论 0 个 reaction 已指派 0 人 在 GitHub 查看

还没有人认领这个 Issue。

评估

难度
4/5
预计耗时
3-5 天
新手友好度
35/100
Issue 类型
缺陷
描述清晰度
基本清楚
活跃度
停滞
技术栈
python, tensorflow
领域
machine-learning

调研方向

检查所引用行中的 tensorflow_model_optimization/python/core/quantization/keras/quantize.py，重点关注对于 subclassed tf.Keras.Model 层，requires_output_quantize 是如何填充和使用的。使用未添加注释的 concatenate 层，在 TensorFlow 2.14 和 tfmot 0.7.5 中复现该行为。完成标准是确定该行为是否符合预期，并通过支持性验证对其进行记录或修正。

由索引模型根据 Issue 内容生成。

描述

bug

Hi all,

I was trying to quantize my model but something strange popped up.

I am using TensorFlow v2.14 and tfmot v0.7.5

I have a sub-classed tf.Keras.Model. It contains some custom layers and other standard layers such as concatenate, activation, etc..

I just want some specific layers to be quantized. For instance, I do not want concatenate to be quantized and 2 other layers. For that, I did not annotate them, so they are not an instance of QuantizeAnnotate.

But strangely, I see that concatenate is an instance of QuantizeWrapperV2. Although, I can also see it is not an instance of QuantizeAnnotate in my cloned function.

So, I do not understand why here : https://github.com/tensorflow/model-optimization/blob/e38d886935c9e2004f72522bf11573d43f46b383/tensorflow_model_optimization/python/core/quantization/keras/quantize.py#L384 we add to requires_output_quantize a layer that it is not an instance of QuantizeAnnotate rather then to check on isinstance as the name suggest? My layers that have not been annotated should be returned from here : https://github.com/tensorflow/model-optimization/blob/e38d886935c9e2004f72522bf11573d43f46b383/tensorflow_model_optimization/python/core/quantization/keras/quantize.py#L377 but during debug, I see that concatenate and other layers, that were not annotated, were added to requires_output_quantize. I believe, this should be wrong.

Now, if we go to this - https://github.com/tensorflow/model-optimization/blob/e38d886935c9e2004f72522bf11573d43f46b383/tensorflow_model_optimization/python/core/quantization/keras/quantize.py#L418C28-L418C52 we can see that if the layer is not in requires_output_quantize and not in layer_quantize_map then we will just retun the layer. But requires_output_quantize holds layers that do NOT need to be quantized from what I am seeing and what this : https://github.com/tensorflow/model-optimization/blob/e38d886935c9e2004f72522bf11573d43f46b383/tensorflow_model_optimization/python/core/quantization/keras/quantize.py#L384 is suggesting.

So I would expect layer.name not in requires_output_quantize to be removed in this if statement:
https://github.com/tensorflow/model-optimization/blob/e38d886935c9e2004f72522bf11573d43f46b383/tensorflow_model_optimization/python/core/quantization/keras/quantize.py#L417
according to my analysis.

In conclusion, I would expect requires_output_quantize to be buggy otherwise there is an explanation for that.

I really appreciate if someone takes the time to explain this. Maybe I am wrong.

I look forward to your feedback.

Thanks,
Idriss

主要语言
Python
星标
1.6k
派生
349
30 天内没有已合并 PR

环境准备

  • 没有 Dockerfile 或 Docker Compose 文件
  • 没有 Pull Request 模板
  • 阅读贡献指南

从这里开始

  1. 先读完整个 Issue，再读项目的贡献指南。
  2. 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
  3. Fork 仓库，在一个分支上完成修改。
  4. 提交 Pull Request，并在描述里引用这个 Issue 编号。

tensorflow/model-optimization 的其他 Issue

查看 tensorflow/model-optimization 的全部 Issue

相似的 Issue

更多 Python Issue

把新 issue 发到你的邮箱

精选适合新手参与的 GitHub issue 摘要。