Large Language Model(LLM) 大语言模型

Text generation 文本生成

• Create LLM-powered Chatbot using OpenVINO, llama-2-7b-chat, red-pajama-3b-chat: 
  ​​​​​​openvino_notebooks/notebooks/254-llm-chatbot/README.md at main · openvinotoolkit/openvino_notebooks · GitHub
• Use GPT-2 to perform text prediction on an input sequence :  
  openvino_notebooks/notebooks/254-llm-chatbot/README.md at main · openvinotoolkit/openvino_notebooks · GitHub
• LLaVA (Large Language and Vision Assistant)  :  
  openvino_notebooks/notebooks/257-llava-multimodal-chatbot/README.md at main · openvinotoolkit/openvino_notebooks · GitHub
• Instruction following using Databricks Dolly 2.0 and OpenVINO™  :  
  openvino_notebooks/notebooks/240-dolly-2-instruction-following at main · openvinotoolkit/openvino_notebooks · GitHub

Measurement  测量

Distance 距离测量

• Monocular depth estimation with images and video:
  openvino_notebooks/notebooks/201-vision-monodepth at main · openvinotoolkit/openvino_notebooks · GitHub

Depth 深度测量

• Depth estimation using VI-depth with OpenVINO™:
  https://github.com/openvinotoolkit/openvino_notebooks/blob/main/notebooks/246-depth-estimation-videpth/README.md

Meter reader 读表器

• read industrial meter's value:https://github.com/openvinotoolkit/openvino_notebooks/blob/main/notebooks/203-meter-reader

Image processing 图像处理

Superresolution 超分辨率

• Upscale raw images with a super resolution model:
  https://github.com/openvinotoolkit/openvino_notebooks/blob/main/notebooks/202-vision-superresolution
• Turn 360p into 1080p video using a super resolution model:
  https://github.com/openvinotoolkit/openvino_notebooks/blob/main/notebooks/202-vision-superresolution
• Upscale small images with superresolution using a PaddleGAN model:
  
  https://github.com/openvinotoolkit/openvino_notebooks/blob/main/notebooks/207-vision-paddlegan-superresolution

Segmentation 分割技术

• Semantic Segmentation with OpenVINO™ using Segmenter:
  https://github.com/openvinotoolkit/openvino_notebooks/blob/main/notebooks/202-vision-superresolution
• Process point cloud data and run 3D Part Segmentation with OpenVINO:
  https://github.com/openvinotoolkit/openvino_notebooks/blob/main/notebooks/224-3D-segmentation-point-clouds
• Universal segmentation with OneFormer:
  https://github.com/openvinotoolkit/openvino_notebooks/blob/main/notebooks/249-oneformer-segmentation/README.md
• Selfie Segmentation Separate the background from users:
  openvino_notebooks/notebooks/243-tflite-selfie-segmentation/243-tflite-selfie-segmentation.ipynb at main · openvinotoolkit/openvino_notebooks · GitHub
• Prompt based object segmentation mask generation using Segment Anything :
  openvino_notebooks/notebooks/237-segment-anything at main · openvinotoolkit/openvino_notebooks · GitHub
   

Anime AI让静态图片动起来

• Turn an image into anime using a GAN:
  openvino_notebooks/notebooks/206-vision-paddlegan-anime at main · openvinotoolkit/openvino_notebooks · GitHub

image fixing/optimization/AI editing 图像修复/优化/AI编辑

• Fill missing pixels with image in-painting:
  openvino_notebooks/notebooks/215-image-inpainting at main · openvinotoolkit/openvino_notebooks · GitHub
• Deblur Images with DeblurGAN-v2:
  https://github.com/openvinotoolkit/openvino_notebooks/blob/main/notebooks/217-vision-deblur
• Use pre-trained models to colorize black & white images:
  openvino_notebooks/notebooks/222-vision-image-colorization at main · openvinotoolkit/openvino_notebooks · GitHub
• Style Transfer with a webcam or video file - live demo:
  openvino_notebooks/notebooks/404-style-transfer-webcam at main · openvinotoolkit/openvino_notebooks · GitHub
• Image editing with InstructPix2Pix:
  
  openvino_notebooks/notebooks/231-instruct-pix2pix-image-editing at main · openvinotoolkit/openvino_notebooks · GitHub

Vehicle detection 车辆检测

• Use pre-trained models to detect and recognize vehicles and their attributes :
  openvino_notebooks/notebooks/218-vehicle-detection-and-recognition at main · openvinotoolkit/openvino_notebooks · GitHub

Human pose estimation 人体姿态评估

• Human pose estimation with a webcam or video file - live demo:
  https://github.com/openvinotoolkit/openvino_notebooks/blob/main/notebooks/402-pose-estimation-webcam
• 3D display of human pose estimation with a webcam or video file:
  https://github.com/openvinotoolkit/openvino_notebooks/blob/main/notebooks/406-3D-pose-estimation-webcam
   

uman action recognition 人体行为识别

• Human action recognition with a webcam or video file - live demo：
  https://github.com/openvinotoolkit/openvino_notebooks/blob/main/notebooks/403-action-recognition-webcam

Human tracking 人体跟踪

• Person tracking with a webcam or video file - live demo：
  https://github.com/openvinotoolkit/openvino_notebooks/blob/main/notebooks/407-person-tracking-webcam

Object detection 物体检测

• Optimize YOLOv7 using NNCF PTQ API：
  https://github.com/openvinotoolkit/openvino_notebooks/blob/main/notebooks/226-yolov7-optimization
• Language-Visual Saliency with CLIP, ask question to recongnize image：
  https://github.com/openvinotoolkit/openvino_notebooks/blob/main/notebooks/232-clip-language-saliency-map
• Object detection with a webcam or video file - live demo：
  https://github.com/openvinotoolkit/openvino_notebooks/blob/main/notebooks/401-object-detection-webcam
• Optimize YOLOv8 using NNCF PTQ API：
  https://github.com/openvinotoolkit/openvino_notebooks/blob/main/notebooks/230-yolov8-optimization
   

OCR 光学字符识别

• Annotate text on images using text recognition resnet：
  https://github.com/openvinotoolkit/openvino_notebooks/blob/main/notebooks/208-optical-character-recognition
• OCR with a webcam or video file - live demo：
  https://github.com/openvinotoolkit/openvino_notebooks/blob/main/notebooks/405-paddle-ocr-webcam
• OCR for handwritten simplified Chinese and Japanese：
  https://github.com/openvinotoolkit/openvino_notebooks/blob/main/notebooks/209-handwritten-ocr
   

Voice processing 声音处理

speech-to-text 语音转文本

• Run inference on speech-to-text recognition model：
  https://github.com/openvinotoolkit/openvino_notebooks/blob/main/notebooks/211-speech-to-text

Multilanguage speech

• The Massively Multilingual Speech (MMS):
  https://github.com/openvinotoolkit/openvino_notebooks/blob/main/notebooks/255-mms-massively-multilingual-speech/README.md

Generate subtitles for video 为视频生成字幕

• Generate subtitles for video with OpenAI Whisper:
  https://github.com/openvinotoolkit/openvino_notebooks/blob/main/notebooks/227-whisper-subtitles-generation

Audio compression 音频压缩

• Audio compression with EnCodec:
  https://github.com/openvinotoolkit/openvino_notebooks/blob/main/notebooks/234-encodec-audio-compression

Voice style change 声音格式变化

• High-Quality Text-Free One-Shot Voice Conversion with FreeVC and OpenVINO™：
  https://github.com/openvinotoolkit/openvino_notebooks/tree/main/notebooks/242-freevc-voice-conversion

speaker diarization 语音分割

• Run inference on speaker diarization pipeline:
  https://github.com/openvinotoolkit/openvino_notebooks/blob/main/notebooks/212-pyannote-speaker-diarization

Text Processing 文字处理

Q&A 自动问答

• Answer your questions basing on a context
  openvino_notebooks/notebooks/213-question-answering at main · openvinotoolkit/openvino_notebooks · GitHub
• Visual Q&A; Visual Question Answering and Image Captioning using BLIP:
  openvino_notebooks/notebooks/233-blip-visual-language-processing at main · openvinotoolkit/openvino_notebooks · GitHub

Text-to-video 文本转音频

• Text-to-video generation with ZeroScope and OpenVINO:
  openvino_notebooks/notebooks/253-zeroscope-text2video/README.md at main · openvinotoolkit/openvino_notebooks · GitHub

Text-to-Music 文本转音乐

• Text-to-Music generation using Riffusion and OpenVINO:
  https://github.com/openvinotoolkit/openvino_notebooks/tree/main/notebooks/241-riffusion-text-to-music
• Controllable Music Generation with MusicGen and OpenVINO™:
  https://github.com/openvinotoolkit/openvino_notebooks/blob/main/notebooks/250-music-generation/README.md

Text-to-speech 文本转语音

• Text-to-Speech generation with BARK and OpenVINO:
  https://github.com/openvinotoolkit/openvino_notebooks/blob/main/notebooks/256-bark-text-to-audio/README.md

Language Translation 语言翻译

• Real-time translation from English to German：
  openvino_notebooks/notebooks/253-zeroscope-text2video/README.md at main · openvinotoolkit/openvino_notebooks · GitHub

Sequence classification 序列分类

• Sequence Classification (positive or negtive auto generated)：
  openvino_notebooks/notebooks/229-distilbert-sequence-classification at main · openvinotoolkit/openvino_notebooks · GitHub

Text-to-image generation 文本到图像生成

• Text-to-image generation with Stable Diffusion method：
  openvino_notebooks/notebooks/225-stable-diffusion-text-to-image at main · openvinotoolkit/openvino_notebooks · GitHub
• Image generation with FastComposer and OpenVINO™：
  openvino_notebooks/notebooks/252-fastcomposer-image-generation/README.md at main · openvinotoolkit/openvino_notebooks · GitHub
• Image generation with Stable Diffusion XL and OpenVINO：
  openvino_notebooks/notebooks/248-stable-diffusion-xl/README.md at main · openvinotoolkit/openvino_notebooks · GitHub
• Text-to-Image Generation and Infinite Zoom with Stable Diffusion v2：
  openvino_notebooks/notebooks/236-stable-diffusion-v2 at main · openvinotoolkit/openvino_notebooks · GitHub
• Image Generation with Tiny-SD：
  openvino_notebooks/notebooks/251-tiny-sd-image-generation/README.md at main · openvinotoolkit/openvino_notebooks · GitHub
• Image generation with Stable Diffusion XL and OpenVINO：
  openvino_notebooks/notebooks/248-stable-diffusion-xl/README.md at main · openvinotoolkit/openvino_notebooks · GitHub
• Image generation with DeepFloyd IF and OpenVINO™：
  openvino_notebooks/notebooks/238-deepfloyd-if at main · openvinotoolkit/openvino_notebooks · GitHub
• A Text-to-Image Generation with ControlNet Conditioning：
  openvino_notebooks/notebooks/235-controlnet-stable-diffusion at main · openvinotoolkit/openvino_notebooks · GitHub

Programming language classification 编程语言分类

• Programming Language Classification with OpenVINO：
  openvino_notebooks/notebooks/247-code-language-id/README.md at main · openvinotoolkit/openvino_notebooks · GitHub

Typo detection 错误检测

• Convert and Optimize Typo Detector with OpenVINO™：
  openvino_notebooks/notebooks/247-code-language-id/README.md at main · openvinotoolkit/openvino_notebooks · GitHub
   

Grammer Correction 语法修正

• Grammatical Error Correction with OpenVINO：
  openvino_notebooks/notebooks/214-grammar-correction at main · openvinotoolkit/openvino_notebooks · GitHub
   

Else 其它

knowledge graph 知识图谱

• Optimize the knowledge graph embeddings model (ConvE):
  openvino_notebooks/notebooks/219-knowledge-graphs-conve at main · openvinotoolkit/openvino_notebooks · GitHub