Skip to content
This repository has been archived by the owner on Nov 25, 2023. It is now read-only.

Support TensorFlow Lite benchmark for android platform

Latest
Compare
Choose a tag to compare
@ysh329 ysh329 released this 28 Sep 00:48
· 3 commits to master since this release

Release bench result of embedded-ai.bench for ncnn/tnn/mnn

注:因为是CSV文件,可以用Excel表格打开。通过对【表格】->【筛选】功能,对表头筛选,进行细致分析。本次不给结论,在不同的手机上,不同框架表现不同。

下图是benchmark的参考示例:

framework branch commit_id model_name platform soc_code soc_name cpu gpu npu product power_mode backend cpu_thread_num avg max min std_dev battery_level system_version repeats warmup imei
mnn master 3ea9dd1 caffe_mobilenetv1 android-armv7 kirin810 kirin810 [email protected][email protected] Mali-G52 D100@Lite SPN-AL00 big_cores ARM 1 249.221 252.995 246.358 1.495 100 9 100 20 A00000B7D25778
mnn master 3ea9dd1 caffe_mobilenetv1 android-armv7 kirin810 kirin810 [email protected][email protected] Mali-G52 D100@Lite SPN-AL00 big_cores ARM 2 125.97 133.192 124.363 1.038 100 9 100 20 A00000B7D25778
mnn master 3ea9dd1 caffe_mobilenetv1 android-armv7 kirin810 kirin810 [email protected][email protected] Mali-G52 D100@Lite SPN-AL00 big_cores ARM 4 70.384 75.003 68.117 1.08 100 9 100 20 A00000B7D25778

定期发布性能数据

  1. 网站:https://ai-performance.com/embedded-ai.bench
  2. 微信:NeuralTalk:
    img