Merge branch 'main' of https://github.com/AllentDan/SegmentationCpp into main

Author: AllentDan

README-Chinese.md

@@ -15,7 +15,7 @@
  - 7 种模型架构可用于单类或者多类的分割任务 (包括Unet)
  - 7 种编码器网络
  - 所有的编码器都有预训练权重，可以更快更好地收敛
- - 相比于python下的GPU前向推理速度具有2倍或以上的优势, cpu下保持速度一致. (Unet测试于RTX 2070S).
+ - 相比于python下的GPU前向推理速度具有30%或以上的提速, cpu下保持速度一致. (Unet测试于RTX 2070S).
 
 ### [📚 Libtorch教程 📚](https://github.com/AllentDan/LibtorchTutorials)
 

README.md

@@ -16,7 +16,7 @@ The main features of this library are:
  - 7 models architectures for binary and multi class segmentation (including legendary Unet)
  - 7 available encoders
  - All encoders have pre-trained weights for faster and better convergence
- - 2x or more faster than pytorch cuda inferece, same speed for cpu. (Unet tested in rtx 2070s).
+ - 35% or more inference speed boost compared with pytorch cuda, same speed for cpu. (Unet tested in rtx 2070s).
 
 ### [📚 Libtorch Tutorials 📚](https://github.com/AllentDan/LibtorchTutorials/tree/master)