mirrors
/
PaddleClas
mirror of https://github.com/PaddlePaddle/PaddleClas.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

Update paddle_quantization_en.md

pull/642/head
littletomatodonkey 2021-03-16 14:07:40 +08:00 committed by GitHub
parent a831632838
commit b3fa7a0114
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docs/en/extension/paddle_quantization_en.md
View File

@ -9,4 +9,4 @@ By using this toolkit, [PaddleClas](https://github.com/PaddlePaddle/PaddleClas)
After quantized, the prediction speed is accelerated from 19.308ms to 14.395ms on SD855. After quantized, the prediction speed is accelerated from 19.308ms to 14.395ms on SD855.
The storage size is reduced from 21M to 10M. The storage size is reduced from 21M to 10M.
The top1 recognition accuracy rate is 75.9%. The top1 recognition accuracy rate is 75.9%.
For specific training methods, please refer to [PaddleSlim quant aware](https://paddlepaddle.github.io/PaddleSlim/quick_start/quant_aware_tutorial.html)。 For specific training methods, please refer to [PaddleSlim quant aware](../../../deploy/slim/quant/README.md)。