PaddlePaddle / Paddle-Lite

PaddlePaddle High Performance Deep Learning Inference Engine for Mobile and Edge (飞桨高性能深度学习端侧推理引擎)
https://www.paddlepaddle.org.cn/lite
Apache License 2.0
6.9k stars 1.6k forks source link

VIM3 and RK3399pro deploy PicoDet ! #9192

Closed 2050airobert closed 5 months ago

2050airobert commented 2 years ago

Hi, 1 请问下picodet下图中为什么只有android armv8的FP16编译版本,不支持android armv7 的FP16编译吗?为什么 image 2 对于amlogic a311d android vim3开发板,可以采用android armv8 FP16编译版本吗? 3 对于rk3399pro android 开发板,可以采用android armv8 FP16编译版本吗? 4 PicoDet 模型有木有 armv7 FP32或者armv7 FP16的nb文件和infer.json 提供呢?可以分享下链接吗? 我只看到arm v8 FP16的nb文件

BR

paddle-bot-old[bot] commented 2 years ago

您好,我们已经收到了您的问题,会安排技术人员尽快解答您的问题,请耐心等待。请您再次检查是否提供了清晰的问题描述、复现代码、环境&版本、报错信息等。同时,您也可以通过查看官网文档常见问题历史Issue来寻求解答。祝您生活愉快~

Hi! We've received your issue and please be patient to get responded. We will arrange technicians to answer your questions as soon as possible. Please make sure that you have posted enough message to demo your request. You may also check out the APIFAQ and Github Issue to get the answer.Have a nice day!

2050airobert commented 2 years ago

hello anyone help?

liyancas commented 2 years ago

1:Paddle Lite支持armv7 + fp16组合,编译选项为:--arch=armv7 --with_arm82_fp16=ON,NDK版本 >=22 2&3:fp16指令针对armv8.2-a以上架构(https://en.wikipedia.org/wiki/ARM_architecture_family#ARMv8-A)以上,而amlogic a311d 和 rk3399pro的ARM架构分别是A73和A72,为armv8-a,因此不能采用FP16编译版本 4:模型没有区别armv8和armv7,fp16 模型需要使用opt工具重新转一下,命令:--valid_targets=arm --enable_fp16=true