ZillaRU / AnnoAnything
万物检测(零样本检测+识别) demo for SG2300X 【Recognize Anything + GroundingDINO】
☆19Updated last year
Alternatives and similar repositories for AnnoAnything
Users that are interested in AnnoAnything are comparing it to the libraries listed below
Sorting:
- 研究GOT-OCR-项目落地加速,不限语言☆60Updated 6 months ago
- 使用SG2300X实现无瑕疵换脸☆30Updated 8 months ago
- Text2speech & tone color conversion demo running on SG2300x 结合openvoice和emotivoice的TTS+即时克隆☆22Updated 6 months ago
- An auto-annotation demo running on SG2300X (YOLOv8/GroundingDINO + MobileSAM)☆10Updated last year
- 模型 llava-Qwen2-7B-Instruct-Chinese-CLIP 增强中文文字识别能力和表情包内涵识别能力,接近gpt4o、claude-3.5-sonnet的识别水平!☆22Updated 9 months ago
- 💡💡💡awesome compute vision app in gradio☆52Updated last year
- segment anything(SAM) for CPP Inference☆30Updated 11 months ago
- Accelerate segment anything model inference using Tensorrt 8.6.1.6☆91Updated last year
- Our 2nd-gen LMM☆33Updated 11 months ago
- 使用OpenCV+onnxruntime部署中文clip做以文搜图,给出一句话来描述想要的图片,就能从图库中搜出来符合要求的图片。包含C++和Python两个版本的程序☆73Updated last year
- 使用ONNXRuntime部署Detic检测2万1千种类别的物体,包含C++和Python两个版本的程序☆17Updated last year
- Mamba-YOLO-World: Marrying YOLO-World with Mamba for Open-Vocabulary Detection☆84Updated 2 months ago
- Train InternViT-6B in MMSegmentation and MMDetection with DeepSpeed☆90Updated 6 months ago
- Python3 package for Chinese/English OCR, with paddleocr-v4 onnx model(~14MB). 基于ppocr-v4-onnx模型推理,可实现 CPU 上毫秒级的 OCR 精准预测,通用场景中英文OCR达到开源SO…☆81Updated 3 months ago
- run ChatGLM2-6B in BM1684X☆49Updated last year
- ☆56Updated last year
- A CPU Realtime VLM in 500M. Surpassed Moondream2 and SmolVLM. Training from scratch with ease.☆196Updated 3 weeks ago
- Python scripts performing Open Vocabulary Object Detection using the YOLO-World model in ONNX.☆54Updated last year
- 适用于sophon bm1684x,基于 Langchain 与 ChatGLM 等语言模型的本地知识库问答☆11Updated 11 months ago
- Here is a demo for PDF parser (Including OCR, object detection tools)☆34Updated 7 months ago
- 中文论文、证券类、财报类PDF数据☆29Updated 11 months ago
- SAM and lama inpaint,包含QT的GUI交互界面,实现了交互式可实时显示结果的画点、画框进行SAM,然后通过进行Inpaint,具体操作看readme里的视频。☆47Updated last year
- 结合 mmdetection 、 label studio 实现数据集自动标注、模型自动迭代的 AI 闭环☆19Updated 2 years ago
- A Simple MLLM Surpassed QwenVL-Max with OpenSource Data Only in 14B LLM.☆37Updated 8 months ago
- ☆173Updated 3 months ago
- ☆119Updated last year
- ☆177Updated last year
- 使用onnxruntime部署GroundingDINO开放世界目标检测,包含C++和Python两个版本的程序☆60Updated last year
- HayLM是专门为儿童训练的大模型,通过对InternLM的训练和微调,结合儿童心理学、教育学以及对话风格的数据训练,实现与儿童的智能互动,并在交流过程中不断学习和适应用户特性,成为一个伴随儿童成长的虚拟朋友。☆12Updated 3 months ago
- Chinese CLIP models with SOTA performance.☆55Updated last year