Comments (2)
shentanyue
commented on June 2, 2024
您好，从报错信息来看，得不到有用的信息。
您可以使用x2paddle先保存成paddle的pd_model模型在cpu上运行看看，排除x2paddle的转换问题后，再使用paddle lite的opt工具将pdmodel转换为nb模型放在安卓环境运行。
转换方式的分辨率一般是与ONNX一致的，精度默认是fp32。 如果自己定义精度，可参考https://www.paddlepaddle.org.cn/lite/v2.12/demo_guides/android_app_demo.html ，使用fp16精度进行部署。
from paddle-lite.
littlecay
commented on June 2, 2024
可以使用x2paddle先保存成paddle的pd_model模型在cpu上运行 这步我之前验证了（用python），没有问题的。
paddle lite的opt工具将pdmodel转换为nb模型 这个就是用paddle官方C++代码，加载成功，调用就会崩溃，是在rk3588+麒麟系统上做的。
关于精度，我知道enable_fp16 设置为 ON，但是直接转化有个参数可以用INT8的精度，不知道这个是不是可以
from paddle-lite.
Related Issues (20)
- predictor.run()之后无结果 HOT 2
- 树莓派4b上跑自己的nb模型结果图片没有识别框 HOT 7
- 使用经过paddle-lite-opt优化后的模型，在压测环境下报错(fread(dst, 1, size, file_) == size): 0!==262288 Failed to read 262288 bytes. HOT 4
- V4 OCR的检测模型，导出为atlas格式后，无法跑在atlas 300ipro上 HOT 1
- arm的推理结果正确，opencl的结果不正确，请问如何做逐层的精度对比分析？ HOT 3
- Object Detection运行run脚本的时候报错 HOT 6
- 华为Atlas300I（3010，昇腾310）安装Paddle-Lite运行例程出错 HOT 4
- [BUG] sort_cpuid_by_max_freq()中的bubble sort代码逻辑错误 HOT 4
- 基于Paddle Lite框架下的编译问题 HOT 3
- Android端推理LightGlue模型crash了 HOT 1
- ubuntu 22.04 x64 编译paddle-lite x86出错 lite/CMakeFiles/publish_inference.dir/rule HOT 2
- .pdmodel转换.nb失败，报错Check failed: it != outputs_.end(): HOT 18
- 3399 编译with_opencl后运行示例mobilenetv1_light_api显示不支持opencl HOT 1
- 使用华为NPU推理pp-yoloe-r模型报错，提示cann版本不匹配 HOT 15
- could not create a descriptor for a pooling forward propagation primitive HOT 1
- "树莓派5 编译错误"- v2.13 编译报错、环境信息: (Linux raspberrypi 6.6.28+rpt-rpi-2712 #1 SMP PREEMPT Debian 1:6.6.28-1+rpt1 (2024-04-22) aarch64 GNU/Linux) HOT 20
- 预编译库的V2,12下载的压缩包里没有找到python,我要怎么继续下一步得到python--->install--->dist--->paddlelite-*.whl HOT 1
- "树莓派5 编译错误"- v2.13 编译报错 cd09a8e01、环境信息:(Debian arm64 ----armv8 ) ，经检查“cd09a8e01”是git describe --always 值 HOT 3
- 编译无法生成inference_lite_lib.armlinux.armv8.opencl包 HOT 5
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from paddle-lite.