From 75466b3ed8c89e4f51f971ef6c5b05d0dfcd8ed8 Mon Sep 17 00:00:00 2001 From: Ethan Yang Date: Thu, 7 Mar 2024 21:04:12 -0800 Subject: [PATCH] update README CN (#1808) --- README_cn.md | 250 +++--------------- .../254-llm-chatbot/254-llm-chatbot.ipynb | 2 +- .../254-llm-chatbot/254-rag-chatbot.ipynb | 2 +- 3 files changed, 37 insertions(+), 217 deletions(-) diff --git a/README_cn.md b/README_cn.md index 223705f6883..7ab2d8eafd0 100644 --- a/README_cn.md +++ b/README_cn.md @@ -8,54 +8,21 @@ 在这里，我们提供了一些可以运行的Jupyter* notebooks，用于学习和尝试使用OpenVINO™开发套件。这些notebooks旨在向各位开发者提供OpenVINO基础知识的介绍，并教会大家如何利用我们的API来优化深度学习推理。 -[![-----------------------------------------------------](https://user-images.githubusercontent.com/10940214/155750931-fc094349-b6ec-4e1f-9f9a-113e67941119.jpg)]() +🚀 您可以通过查看以下交互式的页面，对OpenVINO™ Notebooks的内容进行快速导览： +[OpenVINO™ Notebooks at GitHub Pages](https://openvinotoolkit.github.io/openvino_notebooks/) + +[![notebooks-selector-preview](https://github.com/openvinotoolkit/openvino_notebooks/assets/41733560/a69efb78-1637-404c-b5ef-63974db2bf1b)](https://openvinotoolkit.github.io/openvino_notebooks/) -## 🚀 AI 趋势 - Notebooks -查看最新notebooks代码示例，了解如何在英特尔CPU和GPU上优化和部署最近流行的深度学习模型。 -| **Notebook** | **描述** | **预览** | **补充资料** | -| :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :------------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | -| [YOLOv8 - Optimization](notebooks/230-yolov8-optimization/)
| 利用 NNCF PTQ API 优化 YOLOv8 | | [博客 - 如何用OpenVINO™让YOLOv8获得1000+ FPS性能？](https://mp.weixin.qq.com/s/PSfIZKp4PQtlLdwmn9Z6Bg) | -| [SAM - Segment Anything Model](notebooks/237-segment-anything/)
| 使用 Segment Anything以及OpenVINO™进行基于提示的对象分割掩码生成 | | [博客 - AI分割一切——用OpenVINO™加速Meta SAM大模型 ](https://mp.weixin.qq.com/s/b7EVB6oouUKZGDCFbEi7Yw) | -| [ControlNet - Stable-Diffusion](notebooks/235-controlnet-stable-diffusion/)
| 利用ControlNet条件和OpenVINO™进行文本到图像生成 | | [Blog - Control your Stable Diffusion Model with ControlNet and OpenVINO](https://medium.com/@paularamos_5416/control-your-stable-diffusion-model-with-controlnet-and-openvino-f2aa7e6b1ebd) | -| [Stable Diffusion v2](notebooks/236-stable-diffusion-v2/)
| 利用Stable Diffusion v2 以及 OpenVINO™进行文本到图像生成和无限缩放 | | [博客 - AI作画升级，OpenVINO™ 和英特尔独立显卡助你快速生成视频](https://mp.weixin.qq.com/s/kfyTZK_Ybysceux6ChoLtA) | -| [Whisper - Subtitles generation](notebooks/227-whisper-subtitles-generation/)
| 利用OpenAI Whisper以及OpenVINO™为视频生成字幕 | | | -| [CLIP - zero-shot-image-classification](notebooks/228-clip-zero-shot-image-classification)
| 利用CLIP 以及 OpenVINO™执行零样本图像分类 | | [Blog - Generative AI and Explainable AI with OpenVINO ](https://medium.com/@paularamos_5416/generative-ai-and-explainable-ai-with-openvino-2b5f8e4e720b#:~:text=pix2pix%2Dimage%2Dediting-,Explainable%20AI%20with%20OpenVINO,-Explainable%20AI%20is) | -| [BLIP - Visual-language-processing](notebooks/233-blip-visual-language-processing/)
| 利用BLIP以及OpenVINO™进行视觉问答和图像字幕 | | [Blog - Multimodality with OpenVINO — BLIP](https://medium.com/@paularamos_5416/multimodality-with-openvino-blip-b20bd3a2c87) | -| [Instruct pix2pix - Image-editing](notebooks/231-instruct-pix2pix-image-editing/)
| 利用InstructPix2Pix进行图像编辑 | < | [Blog - Generative AI and Explainable AI with OpenVINO](https://medium.com/@paularamos_5416/generative-ai-and-explainable-ai-with-openvino-2b5f8e4e720b#:~:text=2.-,InstructPix2Pix,-Pix2Pix%20is%20a) | -| [DeepFloyd IF - Text-to-Image generation](notebooks/238-deepfloyd-if/)
| 利用DeepFloyd IF以及OpenVINO™进行文本到图像生成 | | | -| [ImageBind](notebooks/239-image-bind/)
| 使用ImageBind以及OpenVINO™结合多模态数据 | | | -| [Dolly v2](notebooks/240-dolly-2-instruction-following/)
| 使用Databricks Dolly 2.0以及OpenVINO™遵循指令进行文本生成 | | | -| [Stable Diffusion XL](notebooks/248-stable-diffusion-xl/)
| 使用Stable Diffusion XL以及OpenVINO™实现图像生成 | | | -| [MusicGen](notebooks/250-music-generation/)
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/eaidova/openvino_notebooks_binder.git/main?urlpath=git-pull%3Frepo%3Dhttps%253A%252F%252Fgithub.com%252Fopenvinotoolkit%252Fopenvino_notebooks%26urlpath%3Dtree%252Fopenvino_notebooks%252Fnotebooks%2F250-music-generation%2F250-music-generation.ipynb)
[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/openvino_notebooks/blob/main/notebooks/250-music-generation/250-music-generation.ipynb) | 使用MusicGen以及OpenVINO™实现可控音乐生成 | | -|[Tiny SD](notebooks/251-tiny-sd-image-generation/)
[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/openvino_notebooks/blob/main/notebooks/251-tiny-sd-image-generation/251-tiny-sd-image-generation.ipynb) | 使用Tiny-SD以及OpenVINO™实现图像生成 | | | -| [ZeroScope Text-to-video synthesis](notebooks/253-zeroscope-text2video)
| 使用ZeroScope 和 OpenVINO™进行文字到视频生成 | A panda eating bamboo on a rock | -| [LLM chatbot](notebooks/254-llm-chatbot)
| 基于OpenVINO™的大语言模型聊天机器人 | | -| [Bark Text-to-Speech](notebooks/256-bark-text-to-audio/)
| 使用Bark 和 OpenVINO™进行文本到语音转换 | -| [LLaVA Multimodal Chatbot](notebooks/257-llava-multimodal-chatbot/)
| 基于LLaVA和 OpenVINO™的视觉语言助手 | -| [BLIP-Diffusion - Subject-Driven Generation](notebooks/258-blip-diffusion-subject-generation)
| 使用BLIP Diffusion和 OpenVINO™实现基于主题驱动的图像生成和修改 | -| [DeciDiffusion](notebooks/259-decidiffusion-image-generation/)
| 使用DeciDiffusion 和 OpenVINO™进行图像生成 | | -| [Fast Segment Anything](notebooks/261-fast-segment-anything/)
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/eaidova/openvino_notebooks_binder.git/main?urlpath=git-pull%3Frepo%3Dhttps%253A%252F%252Fgithub.com%252Fopenvinotoolkit%252Fopenvino_notebooks%26urlpath%3Dtree%252Fopenvino_notebooks%252Fnotebooks%2F261-fast-segment-anything%2F261-fast-segment-anything.ipynb)
[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/openvino_notebooks/blob/main/notebooks/261-fast-segment-anything/261-fast-segment-anything.ipynb) | 使用FastSAM 和 OpenVINO™进行快速目标分割 | | -| [SoftVC VITS Singing Voice Conversion](notebooks/262-softvc-voice-conversion)
| 基于OpenVINO™实现SoftVC VITS 演唱声音转换 | | -| [Latent Consistency Models: the next generation of Image Generation models ](notebooks/263-latent-consistency-models-image-generation)
| 使用潜在一致性模型以及 OpenVINO™实现高速图像生成 | | -| [QR Code Monster](notebooks/264-qrcode-monster/)
| 使用ControlNet QR Code Monster 和 OpenVINO™生成创意二维码 | | -| [Würstchen](notebooks/265-wuerstchen-image-generation)
| 基于Würstchen 和 OpenVINO™实现文本到图像生成 | | | -| [Distil-Whisper](notebooks/267-distil-whisper-asr)
| 基于Distil-Whisper 和 OpenVINO™实现自动语音识别 | | | -| [FILM](notebooks/269-film-slowmo)
| 使用FILM 和 OpenVINO™实现视频插帧| | + +[![-----------------------------------------------------](https://user-images.githubusercontent.com/10940214/155750931-fc094349-b6ec-4e1f-9f9a-113e67941119.jpg)]() ## 目录 -- [🚀 AI 趋势 - Notebooks](#-ai-趋势---notebooks) - [目录](#目录) - [📝 安装指南](#-安装指南) - [🚀 开始](#-开始) - - [💻 第一步](#-第一步) - - [⌚ 转换 \& 优化](#-转换--优化) - - [🎯 模型演示](#-模型演示) - - [🏃 模型训练](#-模型训练) - - [📺 实时演示](#-实时演示) - [⚙️ 系统要求](#️-系统要求) -- [⚙️ System Requirements](#️-system-requirements) - [💻 运行Notebooks](#-运行notebooks) - [启动单个Notebook](#启动单个notebook) - [启动所有Notebooks](#启动所有notebooks) @@ -69,7 +36,7 @@ ## 📝 安装指南 -OpenVINO Notebooks需要预装Python和Git， 针对不同操作系统的安装参考以下英语指南: +OpenVINO™ Notebooks需要预装Python和Git， 针对不同操作系统的安装参考以下英语指南: | [Windows](https://github.com/openvinotoolkit/openvino_notebooks/wiki/Windows) | [Ubuntu](https://github.com/openvinotoolkit/openvino_notebooks/wiki/Ubuntu) | [macOS](https://github.com/openvinotoolkit/openvino_notebooks/wiki/macOS) | [Red Hat](https://github.com/openvinotoolkit/openvino_notebooks/wiki/Red-Hat-and-CentOS) | [CentOS](https://github.com/openvinotoolkit/openvino_notebooks/wiki/Red-Hat-and-CentOS) | [Azure ML](https://github.com/openvinotoolkit/openvino_notebooks/wiki/AzureML) | [Docker](https://github.com/openvinotoolkit/openvino_notebooks/wiki/Docker) | [Amazon SageMaker](https://github.com/openvinotoolkit/openvino_notebooks/wiki/SageMaker)| | -------------------------------------------------------------------------------- | --------------------------------------------------------------------------- | ------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------ | --------------------------------------------------------------------------- |--------------------------------------------------------------------------- | @@ -79,182 +46,35 @@ OpenVINO Notebooks需要预装Python和Git， 针对不同操作系统的安装 ## 🚀 开始 -Jupyter notebooks 分为四个大类，选择一个跟你需求相关的开始试试吧。祝你好运！ - -
- -### 💻 第一步 - -演示如何使用OpenVINO的Python API进行推理的简短教程。 - -| [001-hello-world](notebooks/001-hello-world/)
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/eaidova/openvino_notebooks_binder.git/main?urlpath=git-pull%3Frepo%3Dhttps%253A%252F%252Fgithub.com%252Fopenvinotoolkit%252Fopenvino_notebooks%26urlpath%3Dtree%252Fopenvino_notebooks%252Fnotebooks%2F001-hello-world%2F001-hello-world.ipynb) | [002-openvino-api](notebooks/002-openvino-api/)
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/eaidova/openvino_notebooks_binder.git/main?urlpath=git-pull%3Frepo%3Dhttps%253A%252F%252Fgithub.com%252Fopenvinotoolkit%252Fopenvino_notebooks%26urlpath%3Dtree%252Fopenvino_notebooks%252Fnotebooks%2F002-openvino-api%2F002-openvino-api.ipynb) | [003-hello-segmentation](notebooks/003-hello-segmentation/)
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/eaidova/openvino_notebooks_binder.git/main?urlpath=git-pull%3Frepo%3Dhttps%253A%252F%252Fgithub.com%252Fopenvinotoolkit%252Fopenvino_notebooks%26urlpath%3Dtree%252Fopenvino_notebooks%252Fnotebooks%2F003-hello-segmentation%2F003-hello-segmentation.ipynb) | [004-hello-detection](notebooks/004-hello-detection/)
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/eaidova/openvino_notebooks_binder.git/main?urlpath=git-pull%3Frepo%3Dhttps%253A%252F%252Fgithub.com%252Fopenvinotoolkit%252Fopenvino_notebooks%26urlpath%3Dtree%252Fopenvino_notebooks%252Fnotebooks%2F004-hello-detection%2F004-hello-detection.ipynb) | -| -------------------------------------------------------------------------------- | --------------------------------------------------------------------------- | ------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------- | -|使用OpenVINO进行图像分类 | 学习使用OpenVINO Python API | 使用OpenVINO进行语义分割 | 使用OpenVINO进行文本检测 | -| | | | | - -
- -### ⌚ 转换 & 优化 - -解释如何使用OpenVINO工具进行模型优化和量化的教程。 - - -| Notebook | Description | -| :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :------------------------------------------------------------------------------- | -| [101-tensorflow-classification-to-openvino](notebooks/101-tensorflow-classification-to-openvino/)
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/eaidova/openvino_notebooks_binder.git/main?urlpath=git-pull%3Frepo%3Dhttps%253A%252F%252Fgithub.com%252Fopenvinotoolkit%252Fopenvino_notebooks%26urlpath%3Dtree%252Fopenvino_notebooks%252Fnotebooks%2F101-tensorflow-classification-to-openvino%2F101-tensorflow-classification-to-openvino.ipynb) | 转换 TensorFlow模型为OpenVINO IR | -| [102-pytorch-to-openvino](notebooks/102-pytorch-to-openvino/)
[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/openvino_notebooks/blob/main/notebooks/102-pytorch-to-openvino/102-pytorch-to-openvino.ipynb) | 转换PyTorch模型为OpenVINO IR | -| [103-paddle-to-openvino](notebooks/103-paddle-to-openvino/)
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/eaidova/openvino_notebooks_binder.git/main?urlpath=git-pull%3Frepo%3Dhttps%253A%252F%252Fgithub.com%252Fopenvinotoolkit%252Fopenvino_notebooks%26urlpath%3Dtree%252Fopenvino_notebooks%252Fnotebooks%2F103-paddle-to-openvino%2F103-paddle-to-openvino-classification.ipynb) | 转换PaddlePaddle模型为OpenVINO IR | -| [104-model-tools](notebooks/104-model-tools/)
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/eaidova/openvino_notebooks_binder.git/main?urlpath=git-pull%3Frepo%3Dhttps%253A%252F%252Fgithub.com%252Fopenvinotoolkit%252Fopenvino_notebooks%26urlpath%3Dtree%252Fopenvino_notebooks%252Fnotebooks%2F104-model-tools%2F104-model-tools.ipynb) | 从Open Model Zoo进行模型下载，转换以及进行基线测试 | -| [105-language-quantize-bert](notebooks/105-language-quantize-bert/) | 优化及量化BERT预训练模型 | -| [106-auto-device](notebooks/106-auto-device/)
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/openvinotoolkit/openvino_notebooks/HEAD?labpath=notebooks%2F106-auto-device%2F106-auto-device.ipynb) | 演示如何使用AUTO设备 | -| [107-speech-recognition-quantization](notebooks/107-speech-recognition-quantization/)
[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/openvino_notebooks/blob/main/notebooks/107-speech-recognition-quantization/107-speech-recognition-quantization-data2vec.ipynb) | 优化及量化预训练Wav2Vec2语音模型 | -| [108-gpu-device](notebooks/108-gpu-device/) | 在GPU上使用OpenVINO™ | -| [109-performance-tricks](notebooks/109-performance-tricks/)| OpenVINO™ 的优化技巧 | -| [110-ct-segmentation-quantize](notebooks/110-ct-segmentation-quantize/)
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/eaidova/openvino_notebooks_binder.git/main?urlpath=git-pull%3Frepo%3Dhttps%253A%252F%252Fgithub.com%252Fopenvinotoolkit%252Fopenvino_notebooks%26urlpath%3Dtree%252Fopenvino_notebooks%252Fnotebooks%2F110-ct-segmentation-quantize%2F110-ct-scan-live-inference.ipynb) | 量化肾脏分割模型并展示实时推理 | -| [112-pytorch-post-training-quantization-nncf](notebooks/112-pytorch-post-training-quantization-nncf/) | 利用神经网络压缩框架(NNCF)在后训练模式下来量化PyTorch模型(无需模型微调) | -| [113-image-classification-quantization](notebooks/113-image-classification-quantization/)
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/openvinotoolkit/openvino_notebooks/HEAD?labpath=notebooks%2F113-image-classification-quantization%2F113-image-classification-quantization.ipynb) | 量化mobilenet图片分类模型 | -| [115-async-api](notebooks/115-async-api/)
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/openvinotoolkit/openvino_notebooks/HEAD?labpath=notebooks%2F115-async-api%2F115-async-api.ipynb)
[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/openvino_notebooks/blob/main/notebooks/115-async-api/115-async-api.ipynb) | 使用异步执行改进数据流水线 | | -| [116-sparsity-optimization](notebooks/116-sparsity-optimization/)
[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/openvino_notebooks/blob/main/notebooks/116-sparsity-optimization/116-sparsity-optimization.ipynb) | 提高稀疏Transformer模型的性能 | -| [117-model-server](notebooks/117-model-server/)| OpenVINO模型服务（OVMS）介绍 | -| [118-optimize-preprocessing](notebooks/118-optimize-preprocessing/)| 提升图片预处理性能 | -| [119-tflite-to-openvino](notebooks/119-tflite-to-openvino/)
[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/openvino_notebooks/blob/main/notebooks/119-tflite-to-openvino/119-tflite-to-openvino.ipynb) | TensorFlow Lite 模型转换为OpenVINO IR | | -| [120-tensorflow-object-detection-to-openvino](notebooks/120-tensorflow-object-detection-to-openvino/)
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/eaidova/openvino_notebooks_binder.git/main?urlpath=git-pull%3Frepo%3Dhttps%253A%252F%252Fgithub.com%252Fopenvinotoolkit%252Fopenvino_notebooks%26urlpath%3Dtree%252Fopenvino_notebooks%252Fnotebooks%2F120-tensorflow-object-detection-to-openvino%2F120-tensorflow-object-detection-to-openvino.ipynb)
[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/openvino_notebooks/blob/main/notebooks/120-tensorflow-object-detection-to-openvino/120-tensorflow-object-detection-to-openvino.ipynb) | TensorFlow目标检测模型转换为OpenVINO IR | -| [121-convert-to-openvino](notebooks/121-convert-to-openvino/)
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/eaidova/openvino_notebooks_binder.git/main?urlpath=git-pull%3Frepo%3Dhttps%253A%252F%252Fgithub.com%252Fopenvinotoolkit%252Fopenvino_notebooks%26urlpath%3Dtree%252Fopenvino_notebooks%252Fnotebooks%2F121-convert-to-openvino%2F121-convert-to-openvino.ipynb)
[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/openvino_notebooks/blob/main/notebooks/121-convert-to-openvino/121-convert-to-openvino.ipynb) | 学习OpenVINO模型转换API | -| [122-quantizing-model-with-accuracy-control](notebooks/122-quantizing-model-with-accuracy-control/)| 使用NNCF工具实现精度感知量化 | -| [123-detectron2-to-openvino](notebooks/123-detectron2-to-openvino/)
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/eaidova/openvino_notebooks_binder.git/main?urlpath=git-pull%3Frepo%3Dhttps%253A%252F%252Fgithub.com%252Fopenvinotoolkit%252Fopenvino_notebooks%26urlpath%3Dtree%252Fopenvino_notebooks%252Fnotebooks%2F123-detectron2-to-openvino%2F123-detectron2-to-openvino.ipynb)
[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/openvino_notebooks/blob/main/notebooks/123-detectron2-to-openvino/123-detectron2-to-openvino.ipynb) | 将Detectron2 转换到 OpenVINO IR | -| [124-hugging-face-hub](notebooks/124-hugging-face-hub/)
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/eaidova/openvino_notebooks_binder.git/main?urlpath=git-pull%3Frepo%3Dhttps%253A%252F%252Fgithub.com%252Fopenvinotoolkit%252Fopenvino_notebooks%26urlpath%3Dtree%252Fopenvino_notebooks%252Fnotebooks%2F124-hugging-face-hub%2F124-hugging-face-hub.ipynb)
[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/openvino_notebooks/blob/main/notebooks/124-hugging-face-hub/124-hugging-face-hub.ipynb) | 使用OpenVINO™加载Hugging Face Model Hub模型 | -| [125-torchvision-zoo-to-openvino](notebooks/125-torchvision-zoo-to-openvino/)
Classification
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/eaidova/openvino_notebooks_binder.git/main?urlpath=git-pull%3Frepo%3Dhttps%253A%252F%252Fgithub.com%252Fopenvinotoolkit%252Fopenvino_notebooks%26urlpath%3Dtree%252Fopenvino_notebooks%252Fnotebooks%2F125-torchvision-zoo-to-openvino%2F125-convnext-classification.ipynb)
[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/openvino_notebooks/blob/main/notebooks/125-torchvision-zoo-to-openvino/125-convnext-classification.ipynb)
Semantic Segmentation
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/eaidova/openvino_notebooks_binder.git/main?urlpath=git-pull%3Frepo%3Dhttps%253A%252F%252Fgithub.com%252Fopenvinotoolkit%252Fopenvino_notebooks%26urlpath%3Dtree%252Fopenvino_notebooks%252Fnotebooks%2F125-torchvision-zoo-to-openvino%2F125-lraspp-segmentation.ipynb)
[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/openvino_notebooks/blob/main/notebooks/125-torchvision-zoo-to-openvino/125-lraspp-segmentation.ipynb)| 将torchvision 分类和语义分割模型转换为OpenVINO IR | -| [126-tensorflow-hub](notebooks/126-tensorflow-hub/)
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/eaidova/openvino_notebooks_binder.git/main?urlpath=git-pull%3Frepo%3Dhttps%253A%252F%252Fgithub.com%252Fopenvinotoolkit%252Fopenvino_notebooks%26urlpath%3Dtree%252Fopenvino_notebooks%252Fnotebooks%2F126-tensorflow-hub%2F126-tensorflow-hub.ipynb)
[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/openvino_notebooks/blob/main/notebooks/126-tensorflow-hub/126-tensorflow-hub.ipynb) | 将TensorFlow Hub 模型转换到OpenVINO IR | -| [128-openvino-tokenizers](notebooks/128-openvino-tokenizers/)
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/eaidova/openvino_notebooks_binder.git/main?urlpath=git-pull%3Frepo%3Dhttps%253A%252F%252Fgithub.com%252Fopenvinotoolkit%252Fopenvino_notebooks%26urlpath%3Dtree%252Fopenvino_notebooks%252Fnotebooks%2F128-opnevino-tokenizers%2F128-opnevino-tokenizers.ipynb)
[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/openvino_notebooks/blob/main/notebooks/128-openvino-tokenizers/128-opnevino-tokenizers.ipynb)| 使用 OpenVINO 分词器将文本处理集成到 OpenVINO 管道中 | -
- -### 🎯 模型演示 - -演示对特定模型的推理。 - - -| Notebook | Description | Preview | -| :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :------------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | -| [201-vision-monodepth](notebooks/201-vision-monodepth/)
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/eaidova/openvino_notebooks_binder.git/main?urlpath=git-pull%3Frepo%3Dhttps%253A%252F%252Fgithub.com%252Fopenvinotoolkit%252Fopenvino_notebooks%26urlpath%3Dtree%252Fopenvino_notebooks%252Fnotebooks%2F201-vision-monodepth%2F201-vision-monodepth.ipynb)
[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/openvino_notebooks/blob/main/notebooks/201-vision-monodepth/201-vision-monodepth.ipynb) | 利用图像和视频进行单目深度估计 | | -| [202-vision-superresolution-image](notebooks/202-vision-superresolution/)
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/eaidova/openvino_notebooks_binder.git/main?urlpath=git-pull%3Frepo%3Dhttps%253A%252F%252Fgithub.com%252Fopenvinotoolkit%252Fopenvino_notebooks%26urlpath%3Dtree%252Fopenvino_notebooks%252Fnotebooks%2F202-vision-superresolution%2F202-vision-superresolution-image.ipynb)
[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/openvino_notebooks/blob/main/notebooks/202-vision-superresolution/202-vision-superresolution-image.ipynb) | 使用超分辨率模型放大原始图像 | → | -| [202-vision-superresolution-video](notebooks/202-vision-superresolution/)
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/eaidova/openvino_notebooks_binder.git/main?urlpath=git-pull%3Frepo%3Dhttps%253A%252F%252Fgithub.com%252Fopenvinotoolkit%252Fopenvino_notebooks%26urlpath%3Dtree%252Fopenvino_notebooks%252Fnotebooks%2F202-vision-superresolution%2F202-vision-superresolution-video.ipynb)
[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/openvino_notebooks/blob/main/notebooks/202-vision-superresolution/202-vision-superresolution-video.ipynb) | 使用超分辨率模型将360p视频转换为1080p视频 | → | -| [203-meter-reader](notebooks/203-meter-reader/)
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/openvinotoolkit/openvino_notebooks/HEAD?labpath=notebooks%2F203-meter-reader%2F203-meter-reader.ipynb) | PaddlePaddle预训练模型读取工业表计数据 | | -|[204-segmenter-semantic-segmentation](notebooks/204-segmenter-semantic-segmentation/)
[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/openvino_notebooks/blob/main/notebooks/204-segmenter-semantic-segmentation/204-segmenter-semantic-segmentation.ipynb) | 基于OpenVINO使用Segmenter的语义分割™ | | -| [205-vision-background-removal](notebooks/205-vision-background-removal/)
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/eaidova/openvino_notebooks_binder.git/main?urlpath=git-pull%3Frepo%3Dhttps%253A%252F%252Fgithub.com%252Fopenvinotoolkit%252Fopenvino_notebooks%26urlpath%3Dtree%252Fopenvino_notebooks%252Fnotebooks%2F205-vision-background-removal%2F205-vision-background-removal.ipynb)
[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/openvino_notebooks/blob/main/notebooks/205-vision-background-removal/205-vision-background-removal.ipynb) | 使用显著目标检测移除并替换图像中的背景 | | -| [206-vision-paddlegan-anime](notebooks/206-vision-paddlegan-anime/)
[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/openvino_notebooks/blob/main/notebooks/206-vision-paddlegan-anime/206-vision-paddlegan-anime.ipynb) | 使用GAN把图片变为动画效果 | → | -| [207-vision-paddlegan-superresolution](notebooks/207-vision-paddlegan-superresolution/)
| 使用PaddleGAN模型以超分辨率放大小图像| | -| [208-optical-character-recognition](notebooks/208-optical-character-recognition/)
| 使用文本识别resnet对图像上的文本进行注释 | | -| [209-handwritten-ocr](notebooks/209-handwritten-ocr/)
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/eaidova/openvino_notebooks_binder.git/main?urlpath=git-pull%3Frepo%3Dhttps%253A%252F%252Fgithub.com%252Fopenvinotoolkit%252Fopenvino_notebooks%26urlpath%3Dtree%252Fopenvino_notebooks%252Fnotebooks%2F209-handwritten-ocr%2F209-handwritten-ocr.ipynb) | 手写体中文及日文OCR | handwritten_simplified_chinese_test
的人不一了是他有为在责新中任自之我们 | -|[210-slowfast-video-recognition](notebooks/210-slowfast-video-recognition/)
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/eaidova/openvino_notebooks_binder.git/main?urlpath=git-pull%3Frepo%3Dhttps%253A%252F%252Fgithub.com%252Fopenvinotoolkit%252Fopenvino_notebooks%26urlpath%3Dtree%252Fopenvino_notebooks%252Fnotebooks%2F210-slowfast-video-recognition%2F210-slowfast-video-recognition.ipynb) | 使用SlowFast以及OpenVINO™进行视频识别 | | -| [211-speech-to-text](notebooks/211-speech-to-text/)
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/eaidova/openvino_notebooks_binder.git/main?urlpath=git-pull%3Frepo%3Dhttps%253A%252F%252Fgithub.com%252Fopenvinotoolkit%252Fopenvino_notebooks%26urlpath%3Dtree%252Fopenvino_notebooks%252Fnotebooks%2F211-speech-to-text%2F211-speech-to-text.ipynb) | 运行语音转文本模型的推理 | | -| [212-pyannote-speaker-diarization](notebooks/212-pyannote-speaker-diarization/)
| 在speaker diarization管道上运行推理 | | -| [213-question-answering](notebooks/213-question-answering/)
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/eaidova/openvino_notebooks_binder.git/main?urlpath=git-pull%3Frepo%3Dhttps%253A%252F%252Fgithub.com%252Fopenvinotoolkit%252Fopenvino_notebooks%26urlpath%3Dtree%252Fopenvino_notebooks%252Fnotebooks%2F213-question-answering%2F213-question-answering.ipynb) | 基于上下文回答问题 | | -| [214-grammar-correction](notebooks/214-grammar-correction/) | 使用OpenVINO进行语法错误纠正 | **input text**: I'm working in campany for last 2 yeas
**Generated text**: I'm working in a company for the last 2 years. | -| [215-image-inpainting](notebooks/215-image-inpainting/)
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/openvinotoolkit/openvino_notebooks/HEAD?labpath=notebooks%2F215-image-inpainting%2F215-image-inpainting.ipynb)| 用绘画中的图像填充缺失像素 | | -| [216-attention-center](notebooks/216-attention-center/)
| 在attention center模型上使用OpenVINO™ | | -| [218-vehicle-detection-and-recognition](notebooks/218-vehicle-detection-and-recognition/)
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/openvinotoolkit/openvino_notebooks/HEAD?labpath=notebooks%2F218-vehicle-detection-and-recognition%2F218-vehicle-detection-and-recognition.ipynb) | 利用OpenVINO及预训练模型检测和识别车辆及其属性 | | -| [219-knowledge-graphs-conve](notebooks/219-knowledge-graphs-conve/)
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/openvinotoolkit/openvino_notebooks/HEAD?labpath=notebooks%2F219-knowledge-graphs-conve%2F219-knowledge-graphs-conve.ipynb) | 使用OpenVINO优化知识图谱嵌入模型(ConvE) || -| [221-machine-translation](notebooks/221-machine-translation)
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/openvinotoolkit/openvino_notebooks/HEAD?labpath=notebooks%2F221-machine-translation%2F221-machine-translation.ipynb)
[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/openvino_notebooks/blob/main/notebooks/221-machine-translation/221-machine-translation.ipynb) | 从英语到德语的实时翻译 | | -| [222-vision-image-colorization](notebooks/222-vision-image-colorization/)
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/openvinotoolkit/openvino_notebooks/HEAD?labpath=notebooks%2F222-vision-image-colorization%2F222-vision-image-colorization.ipynb) | 使用OpenVINO及预训练模型对黑白图像染色 | | -| [223-text-prediction](notebooks/223-text-prediction/)
[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/openvino_notebooks/blob/main/notebooks/223-text-prediction/223-text-prediction.ipynb) | 使用预先训练的模型对输入序列执行文本预测 | | -| [224-3D-segmentation-point-clouds](notebooks/224-3D-segmentation-point-clouds/)
| 使用OpenVINO处理点云数据并进行3D分割 | | -| [225-stable-diffusion-text-to-image](notebooks/225-stable-diffusion-text-to-image)
| 用Stable Diffusion由文本生成图像 | | -| [226-yolov7-optimization](notebooks/226-yolov7-optimization/)
| 使用NNCF PTQ API优化YOLOv7 | | -| [227-whisper-subtitles-generation](notebooks/227-whisper-subtitles-generation/)
[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/openvino_notebooks/blob/main/notebooks/227-whisper-subtitles-generation/227-whisper-convert.ipynb) | 利用OpenAI Whisper及OpenVINO为视频生成字幕 | | -| [228-clip-zero-shot-image-classification](notebooks/228-clip-zero-shot-image-classification)
|利用CLIP及OpenVINO进行零样本图像分类 | | -| [229-distilbert-sequence-classification](notebooks/229-distilbert-sequence-classification/)
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/openvinotoolkit/openvino_notebooks/HEAD?labpath=notebooks%2F229-distilbert-sequence-classification%2F229-distilbert-sequence-classification.ipynb) | 利用OpenVINO进行句子分类 | | -| [230-yolov8-optimization](notebooks/230-yolov8-optimization/)
[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/openvino_notebooks/blob/main/notebooks/230-yolov8-optimization/230-yolov8-object-detection.ipynb) | 使用NNCF PTQ API优化YOLOv8 | | -|[231-instruct-pix2pix-image-editing](notebooks/231-instruct-pix2pix-image-editing/)
| 利用InstructPix2Pix进行图像编辑 | | -|[232-clip-language-saliency-map](notebooks/232-clip-language-saliency-map/)
[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/openvino_notebooks/blob/main/notebooks/232-clip-language-saliency-map/232-clip-language-saliency-map.ipynb) | 基于CLIP和OpenVINO™的视觉语言显著性检测 | | -|[233-blip-visual-language-processing](notebooks/233-blip-visual-language-processing/)
| 基于BLIP和OpenVINO™的视觉问答与图片注释 | | -|[234-encodec-audio-compression](notebooks/234-encodec-audio-compression/)
| 基于EnCodec和OpenVINO™的音频压缩 | | -|[235-controlnet-stable-diffusion](notebooks/235-controlnet-stable-diffusion/)
| 使用ControlNet状态调节Stable Diffusion 实现文字生成图片 | | -|[236-stable-diffusion-v2](notebooks/236-stable-diffusion-v2/)
| 利用Stable Diffusion v2 以及 OpenVINO™进行文本到图像生成和无限缩放使用 | | -|[237-segment-anything](notebooks/237-segment-anything/)
| 使用 Segment Anything以及OpenVINO™进行基于提示的对象分割掩码生成 | | -|[238-deep-floyd-if](notebooks/238-deepfloyd-if/)
| 利用DeepFloyd IF以及OpenVINO™进行文本到图像生成 | | -|[239-image-bind](notebooks/239-image-bind/)
| 利用ImageBind以及OpenVINO™结合多模态数据 | | -|[240-dolly-2-instruction-following](notebooks/240-dolly-2-instruction-following/)
| 使用Databricks Dolly 2.0以及OpenVINO™遵循指令生成文本 | | -|[241-riffusion-text-to-music](notebooks/241-riffusion-text-to-music/)
| 使用Riffusion以及OpenVINO™进行文本到音乐生成 | | -|[242-freevc-voice-conversion](notebooks/242-freevc-voice-conversion/)
| 利用FeeVC和OpenVINO™实现高质量的无文本一次性语音转换 || -| [243-tflite-selfie-segmentation](notebooks/243-tflite-selfie-segmentation/)
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/eaidova/openvino_notebooks_binder.git/main?urlpath=git-pull%3Frepo%3Dhttps%253A%252F%252Fgithub.com%252Fopenvinotoolkit%252Fopenvino_notebooks%26urlpath%3Dtree%252Fopenvino_notebooks%252Fnotebooks%2F243-tflite-selfie-segmentation%2F243-tflite-selfie-segmentation.ipynb)
[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/openvino_notebooks/blob/main/notebooks/243-tflite-selfie-segmentation/243-tflite-selfie-segmentation.ipynb)| 使用TFLite以及OpenVINO™实现Selfie分割方案 | | -| [244-named-entity-recognition](notebooks/244-named-entity-recognition/)
[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/openvino_notebooks/blob/main/notebooks/244-named-entity-recognition/244-named-entity-recognition.ipynb) | 使用OpenVINO™进行命名实体识别 | | -| [245-typo-detector](notebooks/245-typo-detector/)
| 使用OpenVINO™进行英文文本纠错 | | -| [246-depth-estimation-videpth](notebooks/246-depth-estimation-videpth/)
| 使用OpenVINO™进行基于视觉的单目深度估测 | | -| [247-code-language-id](notebooks/247-code-language-id/247-code-language-id.ipynb)
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/eaidova/openvino_notebooks_binder.git/main?urlpath=git-pull%3Frepo%3Dhttps%253A%252F%252Fgithub.com%252Fopenvinotoolkit%252Fopenvino_notebooks%26urlpath%3Dtree%252Fopenvino_notebooks%252Fnotebooks%2F247-code-language-id%2F247-code-language-id.ipynb) | Identify the programming language used in an arbitrary code snippet | || -| [248-stable-diffusion-xl](notebooks/248-stable-diffusion-xl/)
| 使用Stable Diffusion X以及OpenVINO™实现图像生成 | | -| [249-oneformer-segmentation](notebooks/249-oneformer-segmentation/)
| 使用OneFormer以及OpenVINO™实现通用分割任务 | | -| [250-music-generation](notebooks/250-music-generation/)
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/eaidova/openvino_notebooks_binder.git/main?urlpath=git-pull%3Frepo%3Dhttps%253A%252F%252Fgithub.com%252Fopenvinotoolkit%252Fopenvino_notebooks%26urlpath%3Dtree%252Fopenvino_notebooks%252Fnotebooks%2F250-music-generation%2F250-music-generation.ipynb)
[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/openvino_notebooks/blob/main/notebooks/250-music-generation/250-music-generation.ipynb) | 使用MusicGen以及OpenVINO™实现可控音乐生成 | | -|[251-tiny-sd-image-generation](notebooks/251-tiny-sd-image-generation/)
[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/openvino_notebooks/blob/main/notebooks/251-tiny-sd-image-generation/251-tiny-sd-image-generation.ipynb) | 使用Tiny-SD以及OpenVINO™实现图像生成 | | -| [252-fastcomposer-image-generation](notebooks/252-fastcomposer-image-generation/)
| 使用ZeroScope 和 OpenVINO™进行文字到视频生成 | | -| [253-zeroscope-text2video](notebooks/253-zeroscope-text2video)
| Text-to-video synthesis with ZeroScope and OpenVINO™ | A panda eating bamboo on a rock | -| [254-llm-chatbot](notebooks/254-llm-chatbot)
| 基于OpenVINO™的大语言模型聊天机器人 | | -| [255-mms-massively-multilingual-speech](notebooks/255-mms-massively-multilingual-speech/)
| MMS: 使用OpenVINO™将演说技术扩展到1000种语言以上的支持 | | -| [256-bark-text-to-audio](notebooks/256-bark-text-to-audio)
| 使用Bark 和 OpenVINO™进行文本到语音转换 | | -| [257-llava-multimodal-chatbot](notebooks/257-llava-multimodal-chatbot)
| 基于LLaVA和 OpenVINO™的视觉语言助手 | | -| [258-blip-diffusion-subject-generation](notebooks/258-blip-diffusion-subject-generation)
| 使用BLIP Diffusion和 OpenVINO™实现基于主题驱动的图像生成和修改 | | -| [259-decidiffusion-image-generation](notebooks/259-decidiffusion-image-generation)
| 使用DeciDiffusion 和 OpenVINO™进行图像生成 | | -| [260-pix2struct-docvqa](notebooks/260-pix2struct-docvqa)
[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/openvino_notebooks/blob/main/notebooks/260-pix2struct-docvqa/260-pix2struct-docvqa.ipynb)
| 使用Pix2Struct 和 OpenVINO™实现基于文档视觉的问答 | -| [261-fast-segment-anything](notebooks/261-fast-segment-anything/)
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/eaidova/openvino_notebooks_binder.git/main?urlpath=git-pull%3Frepo%3Dhttps%253A%252F%252Fgithub.com%252Fopenvinotoolkit%252Fopenvino_notebooks%26urlpath%3Dtree%252Fopenvino_notebooks%252Fnotebooks%2F261-fast-segment-anything%2F261-fast-segment-anything.ipynb)
[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/openvino_notebooks/blob/main/notebooks/261-fast-segment-anything/261-fast-segment-anything.ipynb) | 使用FastSAM 和 OpenVINO™进行快速目标分割 | | -| [262-softvc-voice-conversion](notebooks/262-softvc-voice-conversion)
| 基于OpenVINO™实现SoftVC VITS 演唱声音转换 | | -| [263-latent-consistency-models-image-generation](notebooks/263-latent-consistency-models-image-generation)
| 使用潜在一致性模型 and OpenVINO™实现高速图像生成 | | -| [264-qrcode-monster](notebooks/264-qrcode-monster/)
| 使用ControlNet QR Code Monster 和 OpenVINO™生成创意二维码 | | -| [265-wuerstchen-image-generation](notebooks/265-wuerstchen-image-generation)
| 基于Würstchen 和 OpenVINO™实现文本到图像生成 | | -| [266-speculative-sampling](notebooks/266-speculative-sampling)
| 基于推测性抽样, KV Caching, 和 OpenVINO™的文本生成任务 | | -| [267-distil-whisper-asr](notebooks/267-distil-whisper-asr)
| 基于Distil-Whisper 和 OpenVINO™实现自动语音识别 | | -| [268-table-question-answering](notebooks/268-table-question-answering)

[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/openvino_notebooks/blob/main/notebooks/268-table-question-answering/268-table-question-answering.ipynb)
| 使用TAPAS 和 OpenVINO™面向表格文件进行问答 || -| [269-film-slowmo](notebooks/269-film-slowmo)
| 使用FILM 和 OpenVINO™实现视频插帧 | | - -
- -### 🏃 模型训练 - -包含训练神经网络代码的教程。 -| Notebook | Description | Preview | -| :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :------------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | -| [301-tensorflow-training-openvino](notebooks/301-tensorflow-training-openvino/) | 从TensorFlow训练花朵分类模型，然后转换为OpenVINO IR | | -| [301-tensorflow-training-openvino-pot](notebooks/301-tensorflow-training-openvino/) | 使用POT量化花朵模型 | | -| [302-pytorch-quantization-aware-training](notebooks/302-pytorch-quantization-aware-training/) | 使用神经网络压缩框架（NNCF）量化PyTorch模型 | | -| [305-tensorflow-quantization-aware-training](notebooks/305-tensorflow-quantization-aware-training/)
[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/openvino_notebooks/blob/main/notebooks/305-tensorflow-quantization-aware-training/305-tensorflow-quantization-aware-training.ipynb) | 使用神经网络压缩框架（NNCF）量化TensorFlow模型 | | - -
- -### 📺 实时演示 -在网络摄像头或视频文件上运行的实时推理演示。 - - -| Notebook | Description | Preview | -| :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :------------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | -| [401-object-detection-webcam](notebooks/401-object-detection-webcam/)
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/eaidova/openvino_notebooks_binder.git/main?urlpath=git-pull%3Frepo%3Dhttps%253A%252F%252Fgithub.com%252Fopenvinotoolkit%252Fopenvino_notebooks%26urlpath%3Dtree%252Fopenvino_notebooks%252Fnotebooks%2F401-object-detection-webcam%2F401-object-detection.ipynb)
[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/openvino_notebooks/blob/main/notebooks/401-object-detection-webcam/401-object-detection.ipynb) | 使用网络摄像头或视频文件进行目标检测 | | -| [402-pose-estimation-webcam](notebooks/402-pose-estimation-webcam/)
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/eaidova/openvino_notebooks_binder.git/main?urlpath=git-pull%3Frepo%3Dhttps%253A%252F%252Fgithub.com%252Fopenvinotoolkit%252Fopenvino_notebooks%26urlpath%3Dtree%252Fopenvino_notebooks%252Fnotebooks%2F402-pose-estimation-webcam%2F402-pose-estimation.ipynb) | 使用网络摄像头或视频文件进行人体姿态估计 | | -| [403-action-recognition-webcam](notebooks/403-action-recognition-webcam/)
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/eaidova/openvino_notebooks_binder.git/main?urlpath=git-pull%3Frepo%3Dhttps%253A%252F%252Fgithub.com%252Fopenvinotoolkit%252Fopenvino_notebooks%26urlpath%3Dtree%252Fopenvino_notebooks%252Fnotebooks%2F403-action-recognition-webcam%2F403-action-recognition-webcam.ipynb) | 使用网络摄像头或视频文件进行动作识别 | | -| [404-style-transfer-webcam](notebooks/404-style-transfer-webcam/)
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/eaidova/openvino_notebooks_binder.git/main?urlpath=git-pull%3Frepo%3Dhttps%253A%252F%252Fgithub.com%252Fopenvinotoolkit%252Fopenvino_notebooks%26urlpath%3Dtree%252Fopenvino_notebooks%252Fnotebooks%2F404-style-transfer-webcam%2F404-style-transfer.ipynb)
[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/openvino_notebooks/blob/main/notebooks/404-style-transfer-webcam/404-style-transfer.ipynb) | 使用网络摄像头或视频文件进行样式变换 | | -| [405-paddle-ocr-webcam](notebooks/405-paddle-ocr-webcam/)
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/openvinotoolkit/openvino_notebooks/HEAD?labpath=notebooks%2F405-paddle-ocr-webcam%2F405-paddle-ocr-webcam.ipynb)
[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/openvino_notebooks/blob/main/notebooks/405-paddle-ocr-webcam/405-paddle-ocr-webcam.ipynb) | 使用网络摄像头或视频文件进行OCR | | -| [406-3D-pose-estimation-webcam](notebooks/406-3D-pose-estimation-webcam/)
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/openvinotoolkit/openvino_notebooks.git/main?labpath=notebooks%2F406-3D-pose-estimation-webcam%2F406-3D-pose-estimation.ipynb) | 使用网络摄像头或视频文件进行3D人体姿态估计 | | -| [407-person-tracking-webcam](notebooks/407-person-tracking-webcam/)
[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/eaidova/openvino_notebooks_binder.git/main?urlpath=git-pull%3Frepo%3Dhttps%253A%252F%252Fgithub.com%252Fopenvinotoolkit%252Fopenvino_notebooks%26urlpath%3Dtree%252Fopenvino_notebooks%252Fnotebooks%2F407-person-tracking-webcam%2F407-person-tracking.ipynb)
[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/openvino_notebooks/blob/main/notebooks/407-person-tracking-webcam/407-person-tracking.ipynb) | 使用网络摄像头或视频文件进行人体跟踪 | | +使用这个 [页面](https://openvinotoolkit.github.io/openvino_notebooks/)来探索notebooks, 选择一个跟你需求相关的开始试试吧。祝你好运！ + +**注意: 这个仓库的main分支已经升级了对于OpenVINO 2024.0 release的支持.** 请运行在你的 `openvino_env`虚拟环境中，运行 `pip install --upgrade -r requirements.txt` 升级到最新版本. 如果这是您第一次安装OpenVINO™ Notebooks，请参考以下的 [安装指南](#-installation-guide)。 如果您想使用上一个OpenVINO版本, 请切换至[2023.3 分支](https://github.com/openvinotoolkit/openvino_notebooks/tree/2023.3). 如果您想使用上一个长期维护 (LTS) 的OpenVINO版本，请切换到 [2022.3 分支](https://github.com/openvinotoolkit/openvino_notebooks/tree/2022.3)。 + +如果您有任何问题，可以开启一个 GitHub [讨论](https://github.com/openvinotoolkit/openvino_notebooks/discussions)。 + -如果你遇到了问题，请查看[故障排除](#-troubleshooting), [常见问题解答](#-faq) 或者创建一个GitHub [discussion](https://github.com/openvinotoolkit/openvino_notebooks/discussions)。 +如果你遇到了问题，请查看[故障排除](#-troubleshooting), [常见问题解答](#-faq) 或者创建一个GitHub [讨论](https://github.com/openvinotoolkit/openvino_notebooks/discussions)。 -带有![binder logo](https://mybinder.org/badge_logo.svg) 按键的Notebooks可以在无需安装的情况下运行。[Binder](https://mybinder.org/) 是一项资源有限的免费在线服务。 如果享有获得最佳性能体验，请遵循[安装指南](#-installation-guide)在本地运行Notebooks。 +带有![binder 标签](https://mybinder.org/badge_logo.svg) 和[colab 标签](https://colab.research.google.com/assets/colab-badge.svg) 按键的Notebooks可以在无需安装的情况下运行。[Binder](https://mybinder.org/) 和[Google Colab](https://colab.research.google.com/)是基于有限资源的免费在线服务。 如果享有获得最佳性能体验，请遵循[安装指南](#-installation-guide)在本地运行Notebooks。 [![-----------------------------------------------------](https://user-images.githubusercontent.com/10940214/155750931-fc094349-b6ec-4e1f-9f9a-113e67941119.jpg)]()
## ⚙️ 系统要求 -## ⚙️ System Requirements 这些notebooks可以运行在任何地方，包括你的笔记本电脑，云VM，或者一个Docker容器。下表列出了所支持的操作系统和Python版本。 | 支持的操作系统 | [Python Version (64-bit)](https://www.python.org/) | -| :--------------------------------------------------------- | :------------------------------------------------- | -| Ubuntu 20.04 LTS, 64-bit | 3.8 - 3.10 | -| Ubuntu 22.04 LTS, 64-bit | 3.8 - 3.10 | -| Red Hat Enterprise Linux 8, 64-bit | 3.8 - 3.10 | -| CentOS 7, 64-bit | 3.8 - 3.10 | -| macOS 10.15.x versions or higher | 3.8 - 3.10 | -| Windows 10, 64-bit Pro, Enterprise or Education editions | 3.8 - 3.10 | -| Windows Server 2016 or higher | 3.8 - 3.10 | +| :--------------------------------------------------------- |:---------------------------------------------------| +| Ubuntu 20.04 LTS, 64-bit | 3.8 - 3.11 | +| Ubuntu 22.04 LTS, 64-bit | 3.8 - 3.11 | +| Red Hat Enterprise Linux 8, 64-bit | 3.8 - 3.11 | +| CentOS 7, 64-bit | 3.8 - 3.11 | +| macOS 10.15.x versions or higher | 3.8 - 3.11 | +| Windows 10, 64-bit Pro, Enterprise or Education editions | 3.8 - 3.11 | +| Windows Server 2016 or higher | 3.8 - 3.11 | [![-----------------------------------------------------](https://user-images.githubusercontent.com/10940214/155750931-fc094349-b6ec-4e1f-9f9a-113e67941119.jpg)](#) @@ -276,7 +96,7 @@ jupyter 201-vision-monodepth.ipynb jupyter lab notebooks ``` -在浏览器中，从Jupyter Lab侧边栏的文件浏览器中选择一个notebook文件，每个notebook文件都位于notebooks目录中的子目录中。 +在浏览器中，从Jupyter Lab侧边栏的文件浏览器中选择一个notebook文件，每个notebook文件都位于`notebooks` 目录中的子目录中。 @@ -289,23 +109,23 @@ jupyter lab notebooks 1. 停止Jupyter Kernel - 按 Ctrl-c 结束 Jupyter session，会弹出一个提示框 Shutdown this Jupyter server (y/[n])? 输入 y 并按 回车。 + 按 `Ctrl-c`结束 Jupyter session，会弹出一个提示框 `Shutdown this Jupyter server (y/[n])?`，您可以输入 `y` and 敲击 `Enter`回车。
2. 注销虚拟环境 - 注销虚拟环境：只需在激活了 openvino_env 的终端窗口中运行 deactivate 即可。 + 注销虚拟环境：只需在激活了`openvino_env`的终端窗口中运行 `deactivate`即可。 - 重新激活环境：在Linux上运行 source openvino_env/bin/activate 或者在Windows上运行 openvino_env\Scripts\activate 即可，然后输入 jupyter lab 或 jupyter notebook 即可重新运行notebooks。 + 重新激活环境：在Linux上运行 `source openvino_env/bin/activate` 或者在Windows上运行 `openvino_env\Scripts\activate` 即可，然后输入 `jupyter lab` 或 `jupyter notebook` 即可重新运行notebooks。
-
+
3. 删除虚拟环境 _(可选)_ - 直接删除 openvino_env 目录即可删除虚拟环境： + 直接删除 `openvino_env` 目录即可删除虚拟环境：
@@ -341,14 +161,14 @@ jupyter lab notebooks ## ⚠️ 故障排除 -如果以下方法无法解决您的问题，欢迎创建一个[discussion topic](https://github.com/openvinotoolkit/openvino_notebooks/discussions) +如果以下方法无法解决您的问题，欢迎创建一个[讨论主题](https://github.com/openvinotoolkit/openvino_notebooks/discussions) 或[issue](https://github.com/openvinotoolkit/openvino_notebooks/issues)! -- 运行 python check_install.py 可以帮助检查一些常见的安装问题，该脚本位于openvino_notebooks 目录中。 - 记得运行该脚本之前先激活 openvino_env 虚拟环境。 -- 如果出现 ImportError ，请检查是否安装了 Jupyter Kernel。如需手动设置kernel，从 Jupyter Lab 或 Jupyter Notebook 的_Kernel->Change Kernel_菜单中选择openvino_env内核。 -- 如果OpenVINO是全局安装的，不要在执行了setupvars.bat或setupvars.sh的终端中运行安装命令。 -- 对于Windows系统，我们建议使用_Command Prompt (cmd.exe)，而不是_PowerShell。 +- 运行 `python check_install.py` 可以帮助检查一些常见的安装问题，该脚本位于openvino_notebooks 目录中。 + 记得运行该脚本之前先激活 `openvino_env` 虚拟环境。 +- 如果出现 `ImportError` ，请检查是否安装了 Jupyter Kernel。如需手动设置kernel，从 Jupyter Lab 或 Jupyter Notebook 的_Kernel->Change Kernel_菜单中选择`openvino_env`内核。 +- 如果OpenVINO是全局安装的，不要在执行了`setupvars.bat`或`setupvars.sh`的终端中运行安装命令。 +- 对于Windows系统，我们建议使用_Command Prompt (`cmd.exe`)，而不是_PowerShell。 [![-----------------------------------------------------](https://user-images.githubusercontent.com/10940214/155750931-fc094349-b6ec-4e1f-9f9a-113e67941119.jpg)](#-contributors)
diff --git a/notebooks/254-llm-chatbot/254-llm-chatbot.ipynb b/notebooks/254-llm-chatbot/254-llm-chatbot.ipynb index f001628ae97..e36485b1534 100644 --- a/notebooks/254-llm-chatbot/254-llm-chatbot.ipynb +++ b/notebooks/254-llm-chatbot/254-llm-chatbot.ipynb @@ -1446,7 +1446,7 @@ "# if you have any issue to launch on your platform, you can pass share=True to launch method:\n", "# demo.launch(share=True)\n", "# it creates a publicly shareable link for the interface. Read more in the docs: https://gradio.app/docs/\n", - "demo.launch(server_name='10.3.233.99', server_port=5677)" + "demo.launch()" ] }, { diff --git a/notebooks/254-llm-chatbot/254-rag-chatbot.ipynb b/notebooks/254-llm-chatbot/254-rag-chatbot.ipynb index f1156ffe4e9..feb37f8404b 100644 --- a/notebooks/254-llm-chatbot/254-rag-chatbot.ipynb +++ b/notebooks/254-llm-chatbot/254-rag-chatbot.ipynb @@ -297,7 +297,7 @@ "\n", "llm_model_id = widgets.Dropdown(\n", " options=llm_model_ids,\n", - " value=llm_model_ids[0],\n", + " value=llm_model_ids[4],\n", " description=\"Model:\",\n", " disabled=False,\n", ")\n",