Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
xxr 513500cb00 | 1 year ago | |
---|---|---|
.. | ||
LIC2020 | 1 year ago | |
ascend310_lite_subgraph/image_classification_demo | 1 year ago | |
cuda_linux_demo | 1 year ago | |
custom-operator | 1 year ago | |
ernie-varlen | 1 year ago | |
lib | 1 year ago | |
paddle-trt | 1 year ago | |
paddle_infer_demo | 1 year ago | |
resnet50 | 1 year ago | |
sparsity | 1 year ago | |
test/shrink_memory | 1 year ago | |
x86_gru_int8 | 1 year ago | |
x86_linux_demo | 1 year ago | |
yolov3 | 1 year ago | |
README.md | 1 year ago | |
run_demo.sh | 1 year ago |
如果您看到这个目录,我们会假设您已经对Paddle Inference有了一定的了解。
如果您刚刚接触Paddle Inference不久,建议您访问这里对Paddle Inference做一个初步的认识。
这个目录包含了图像中使用的分类,检测,以及NLP中Ernie/Bert模型测试样例,同时也包含了Paddle-TRT,多线程等测试样例。
为了能够顺利运行样例,请您在环境中准备Paddle Inference C++预编译库。
一:获取编译库:
二:预编译lib目录结构介绍:
进入预编译库,目录结构为:
├── CMakeCache.txt
├── paddle
├── third_party
└── version.txt
其中paddle
目录包含了预编译库的头文件以及lib文件。
third_party
包含了第三方依赖库的头文件以及lib文件。
version.txt
包含了lib的相关描述信息,包括:
```
GIT COMMIT ID: 06897f7c4ee41295e6e9a0af2a68800a27804f6c
WITH_MKL: ON # 是否带MKL
WITH_MKLDNN: OFF # 是否带MKLDNN
WITH_GPU: ON # 是否支持GPU
CUDA version: 10.1 # CUDA的版本
CUDNN version: v7。 # CUDNN版本
WITH_TENSORRT: ON # 是否带TRT
```
有了预编译库后我们开始进入各个目录进行样例测试吧~
使用paddledetection在jetson nano上部署目标检测网络,检测简单手势,然后再通过nano控制beep等外设,来达到beep的变频输出
Markdown C++ Python reStructuredText Shell other
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》