Skip to content

Issues: PaddlePaddle/Paddle-Lite

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

184 Open 2,305 Closed
184 Open 2,305 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

paddlelite是否支持没有操作系统的arm编译
#10615 opened Dec 27, 2024 by xukui1203
激活函数量化后的执行源码和原理公式可以分享吗？
#10614 opened Dec 23, 2024 by sdreamforchen
1
当运行文字识别的时候，经过det会得出boxes，然后能不能多线程进行rec处理，把boxes分为x个部分然后创建x个线程来跑，来提高rec的识别效率，有没有可行性
#10613 opened Dec 11, 2024 by manongxiaobaigbc
@ddchenhao66
3
onnx模型使用paddlelit opt量化后推理结果错误,windows x86平台
#10612 opened Dec 10, 2024 by Lizuole007
@ddchenhao66
2
mac使用ndk编译出错
#10610 opened Dec 7, 2024 by java-tianz
@ddchenhao66
1
paddle lite 推理预处理图片时，是否直接调用paddle_image_preprocess.h处理的方法，不再引用单独的opencv库？我看的demo里是单独引用了一个opencv库，这样的话打包出来就会多2M，能否提供一个使用paddle_image_preprocess.h预处理图片的demo？
#10609 opened Dec 6, 2024 by orq518
@ddchenhao66
1
pip 没有上传适合 m1 mac 的arm64的安装包，直接使用pip安装会失败
#10608 opened Dec 6, 2024 by dev-xdyang
@ddchenhao66
1
我已经实现了python的表格识别，我现在需要移植到paddle lite上，已经用opt将表格识别模型转换了，也写了c++demo来进行预测推理，但是与paddleocr上python推理的结果不一样，输入图片的初始化已经和python的操作一样，先将图片的最大边为488，然后进行标准化，然后进行填充为488x488大小，然后进行预测，c++图片处理后的数据和python处理后的数据几乎一样，但推理后的结果还是有很大差别，会不会是opt转换之后会不会对推理结果造成影响
#10605 opened Dec 2, 2024 by manongxiaobaigbc
@MuShangCC
27
x86版本, 设置--with_avx=OFF, 编译不过, 代码里面含有大量avx相关代码.
#10603 opened Nov 26, 2024 by mixml
@zhupengyang
3
.nb模型运行时报错PaddleLiteV2.12 remove XShape OutputTensor for SqueezeOp status/reopen
#10602 opened Nov 22, 2024 by DarrenZhangug
@zhupengyang
2
Paddle-Lite能否在arm设备上使用表格检测
#10599 opened Nov 21, 2024 by Whisper-jack
8
单模型拆分到多个硬件上部署的问题
#10598 opened Nov 21, 2024 by chenglopl
1
如何接入整图编译类型的硬件后端
#10597 opened Nov 19, 2024 by chayliu1991
2
paddle-lite 当前可以用于大模型部署吗，未来是否有相关的开发计划
#10596 opened Nov 19, 2024 by chayliu1991
1
运行paddle_lite_ocr，报模型opt版本和paddle-lite不一致问题
#10594 opened Nov 18, 2024 by Whisper-jack
9
运行报错‘io_copy’ is not supported by Paddle-Lite
#10593 opened Nov 16, 2024 by Whisper-jack
1
Paddle-Lite在Docker 统一编译环境搭建失败
#10592 opened Nov 15, 2024 by wwma
14
Paddle Lite v2.9 ArmLinux编译部署 API的链接问题
#10589 opened Nov 12, 2024 by Enoch9x9
2
build_windows.bat在输入非默认visual studio路径后退出
#10586 opened Nov 7, 2024 by huxiangdong
1
2.14rc在rk3399上推理官方的yolov5u_n报错
#10585 opened Nov 6, 2024 by leslie2046
13
yolov11转出的模型，用2.14的opt转到nb模型，android demo运行预测时崩溃
#10584 opened Nov 2, 2024 by nielev
1
昇腾310P3无法使用dynamic shape
#10583 opened Oct 31, 2024 by ly303550688
@hong19860320
1
官方的yolov5n模型我自己用opt转换后使用报错
#10580 opened Oct 30, 2024 by leslie2046
@hong19860320
7
使用opt工具转换个人定制模型失败
#10579 opened Oct 28, 2024 by wwma
@hong19860320
5
全志A133 OPENCL性能测试
#10578 opened Oct 23, 2024 by fangbaolei
@ddchenhao66
4
ProTip! no:milestone will show everything without a milestone.