search

Tencent / TNN

TNN: developed by Tencent Youtu Lab and Guangying Lab, a uniform deep learning inference framework for mobile、desktop and server. TNN is distinguished by several outstanding features, including its cross-platform capability, high performance, model compression and code pruning. Based on ncnn and Rapidnet, TNN further strengthens the support and performance optimization for mobile devices, and also draws on the advantages of good extensibility and high performance from existed open source efforts. TNN has been deployed in multiple Apps from Tencent, such as Mobile QQ, Weishi, Pitu, etc. Contributions are welcome to work in collaborative with us and make TNN a better framework.
Other
4.42k stars 771 forks source link

Android demo: Blazeface 图片和视频输入推理时间差异 #576

Open yyqgood opened 4 years ago

yyqgood commented 4 years ago

你好： 测试平台：华为P20

  1. 我首先使用了benchmark测试了1/2/4线程的Blazeface，大概在10ms到4ms之间，我认为这是正确的
  2. 之后我还是在此平台下安装了Android demo，测试了图片输入推理时间大概在8-9ms（我认为这是正确的）；但视频输入推理时间却大概在50ms左右； 我认为推理时间差异有些大？请问你们测试有这个问题吗？还是我忽视了什么？ 期待你们的回复，谢谢！
yyqgood commented 4 years ago
  1. 我还在issue#478 看到：优图人脸配准的摄像头案例是blazeface和facealign两个sdk组合的；而我还是在此平台下，测试了人脸配准的视频输入推理时间在30ms左右； 我到底错过了什么？
yyqgood commented 3 years ago

@hzlzh @bluaxe @kirozhao @nihui

neiltian-tencent commented 3 years ago

@yyqgood 无法复现此问题，需提供更多信息，把fps错看成了时间？