Texonom
Texonom
/
Engineering
Engineering
/Data Engineering/Artificial Intelligence/AI Development/AI Optimization/Model Quantization/Model Quantization Method/
Post-training quantization
Search

Post-training quantization

Creator
Creator
Seonglae Cho
Created
Created
2023 Jul 2 3:4
Editor
Editor
Seonglae Cho
Edited
Edited
2024 Jan 15 16:21
Refs
Refs
Quantization Aware Training

PTQ, Static Quantization

Involves quantizing the weights and activations of the model
파라미터 size 큰 대형 모델에 대해서는 정확도 하락의 폭이 작지만 작으면 하락폭 크다
PTQ Notion
Quantization Module Fusion
Mixed-precision decomposition
 
 
 
 
 
Post-training quantization  |  TensorFlow Model Optimization
Post-training quantization  |  TensorFlow Model Optimization
https://www.tensorflow.org/model_optimization/guide/quantization/post_training
Post-training quantization  |  TensorFlow Model Optimization
딥러닝의 Quantization (양자화)와 Quantization Aware Training
gaussian37's blog
딥러닝의 Quantization (양자화)와 Quantization Aware Training
https://gaussian37.github.io/dl-concept-quantization/
딥러닝의 Quantization (양자화)와 Quantization Aware Training
 
 
 

Backlinks

Model Quantization AlgorithmModel Quantization AlgorithmModel Quantization Method

Recommendations

Texonom
Texonom
/
Engineering
Engineering
/Data Engineering/Artificial Intelligence/AI Development/AI Optimization/Model Quantization/Model Quantization Method/
Post-training quantization
Copyright Seonglae Cho