Comments (7)
Post-training quantization is a conversion technique that can reduce model size while also improving CPU and hardware accelerator latency, with little degradation in model accuracy.
From https://www.tensorflow.org/lite/performance/post_training_quantization
I am not a researcher in the direction of model quantization. At first I thought the official description you posted was correct, but after a lot of experiments( a classification task), I found the quantized results could go down as well as up(I can't post my experiment results here because of corporate data security). After discuss with my colleague, we think the quantization operation can be treated as reducing overfitting like L1,L2, but this is just speculation. However I think the official description should be verified again. Maybe I should open a issue in tensorflow github repository.
from tensorflow-handbook.
@burui11087 Could you tell me on which condition the quantized size will be bigger than the original one?
from tensorflow-handbook.
Post-training quantization is a conversion technique that can reduce model size while also improving CPU and hardware accelerator latency, with little degradation in model accuracy.
From https://www.tensorflow.org/lite/performance/post_training_quantization
from tensorflow-handbook.
Post-training quantization is a conversion technique that can reduce model size while also improving CPU and hardware accelerator latency, with little degradation in model accuracy.
From https://www.tensorflow.org/lite/performance/post_training_quantization
I think that's my fault after reread https://tf.wiki/zh/deployment/lite.html#quantization . I find what you talk about is post-training quantization, it will cause accuracy loss. I use quantization-aware training in my daily work, that will make the accuracy better or worse.
from tensorflow-handbook.
@burui11087 Could you tell me on which condition the quantized size will be bigger than the original one?
not quantized size, it's accuracy.
from tensorflow-handbook.
@burui11087
Yes, I just try to talk about post training quantization here.
Thank you for your careful reviewing. I am a beginner in tflite. If you have found any issue in this chapter, or have any idea, please let me know.
from tensorflow-handbook.
@snowkylin maybe we need add training-aware-quantization content later.
from tensorflow-handbook.
Related Issues (20)
- 书籍下载 HOT 2
- Chapter Review (Richard): Swift for Tensorflow
- 最新版的tf2.0版本有对应的PDF下载吗? HOT 1
- chapter basic 中的均方差损失函数是不是有问题? HOT 1
- 能否创办讨论区 HOT 1
- 多机训练问题
- android sample code is be removed HOT 1
- 报错TypeError: slice indices must be integers or None or have an __index__ method
- 设置显存使用策略
- tf.keras
- may could prefer model.save but not tf.saved_model.save
- 继承 tf.keras.Model 类建立的 Keras 模型的模型保存和导入的问题
- MNISTLoader类中的get_batch方法取出的数据存在重复项 HOT 1
- TensorFlow Handbook
- epsilon值的计算应该不是初始的固定值吧?
- fix 404
- Swift 是静态语言哦:)
- Is the book `Concise TensorFlow 2` available in English? HOT 4
- 教程答疑区无法显示网页 HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from tensorflow-handbook.