openvino API 2.0 与之前版本API差异对比

🥇 版权: 本文由【墨理学AI】原创首发、各位读者大大、敬请查阅、感谢三连
🎉 声明: 作为全网 AI 领域 干货最多的博主之一，❤️ 不负光阴不负卿 ❤️

文章目录

2. Read a model from a drive

3. Load the Model to the Device

4. Create an Inference Request

5. Fill input tensors

6. Start Inference—同步和异步推理

7. Process the Inference Results

精选专栏

0. python 项目 openvino 的安装

使用 pip 命令进行安装即可，下载安装速度慢、则考虑指定源

pip install  openvino-dev
 pip install  openvino
 # 模型转换会用到 
 pip install  onnx
 pip install onnxruntime
 

openvino API 2.0 与之前版本API差异对比

openvino API 2.0 和之前 版本差异较大，本博文属于官方文档的Python版本代码摘录，方便部分官网网络不可达的同学查阅，有个基本了解

1. Create Core

Inference Engine API:

import numpy as np
 import openvino.inference_engine as ie
 core = ie.IECore()
 

OpenVINO™ Runtime API 2.0:

import openvino.runtime as ov
 core = ov.Core()
 

1.1 (Optional) Load extensions (扩展算子)

Inference Engine API:

core.add_extension("path_to_extension_library.so", "CPU")
 

OpenVINO™ Runtime API 2.0:

core.add_extension("path_to_extension_library.so")
 

2. Read a model from a drive

Inference Engine API:

network = core.read_network("model.xml")
 

OpenVINO™ Runtime API 2.0:

model = core.read_model("model.xml")
 

2.1 (Optional) Perform model preprocessing

3. Load the Model to the Device

Inference Engine API:

# Load network to the device and create infer requests
 exec_network = core.load_network(network, "CPU", num_requests=4)
 

OpenVINO™ Runtime API 2.0:

compiled_model = core.compile_model(model, "CPU")
 

4. Create an Inference Request

Inference Engine API:

# Done in the previous step
 

OpenVINO™ Runtime API 2.0:

infer_request = compiled_model.create_infer_request()
 

5. Fill input tensors

6. Start Inference—同步和异步推理

7. Process the Inference Results

---

精选专栏

---

计算机视觉领域 八大专栏、不少干货、有兴趣可了解一下