Pillars-Creation / Visualglm-image-to-textLinks
补充了一些Visualglm缺少的文件，可以对Visualglm进行训练，实例中是对人脸做了面相的识别
☆13Updated 2 years ago
Alternatives and similar repositories for Visualglm-image-to-text
Users that are interested in Visualglm-image-to-text are comparing it to the libraries listed below
Sorting:
- 可以成功Lora微调的Qwen-VL模型☆16Updated 2 years ago
- Workshop on Foundation Model 1st foundation model challenge Track1 codebase (Open TransMind v1.0)☆18Updated 2 years ago
- 使用DBNet检测条形码，包含C++和Python两种版本的程序☆37Updated 4 years ago
- 国内外数据竞赛资讯整理☆18Updated 4 years ago
- ☆30Updated last year
- 陆续 开源医疗行业的深度学习模型及数据集☆13Updated 3 years ago
- 集成了LLM与SDXL的AIGC应用程序☆29Updated last year
- 安卓手机部署DeepSeek-R1 蒸馏的1.5B模型☆22Updated 9 months ago
- 本项目是关于Yi的多模态系列模型，如Yi-VL-6B/34B等的实验与应用。☆14Updated last year
- convert paddleOCR to torchOCR, ppocr-v3,ppocr-v4, onnx, openvino☆33Updated 2 years ago
- 此项目用于自动化采集、处理和可视化医疗问答数据，可助力构建高质量医疗问答对数据集。同时提供使用预处理后的数据集对Qwen-7B-Chat进行微调的详细说明。☆20Updated 10 months ago
- 使用FastAPI+vLLM部署Qwen2.5☆24Updated last year
- Multimodal chatbot with computer vision capabilities integrated, our 1st-gen LMM☆101Updated last year
- 口罩检测。凑个热闹，和百度类似的是否佩戴口罩检测分类，但是速度会更快。☆30Updated last year
- 使用ONNXRuntime部署E2Pose人体关键点检测，一共包含20个onnx模型，依然是C++和Python两个版本的程序☆16Updated 2 years ago
- 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！☆27Updated last year
- 天池 NVIDIA TensorRT Hackathon 2023 —— 生成式AI模型优化赛 初赛第三名方案☆50Updated 2 years ago
- Bert TensorRT模型加速部署☆10Updated 3 years ago
- Xtuner Factory☆35Updated last year
- Here is a demo for PDF parser (Including OCR, object detection tools)☆36Updated last year
- Chinese CLIP models with SOTA performance.☆59Updated 2 years ago
- 海思设备上部署阉割版yolov5☆13Updated 3 years ago
- ☆14Updated 6 years ago
- 基于MindSpore AI框架实现零售商品识别 top1方案☆47Updated 3 years ago
- Intelligent Video Analytics toolkit based on different inference backends.☆27Updated 2 years ago
- ☆13Updated 4 years ago
- ☆29Updated 3 years ago
- ☆57Updated last year
- A Simple MLLM Surpassed QwenVL-Max with OpenSource Data Only in 14B LLM.☆38Updated last year
- 基于Yolov5-Deepsort-Fastreid源码，重构了视频行人MOT和行人ReID特征提取代码、接口☆12Updated 2 years ago