breezedeus / Coin-CLIPLinks
Coin-CLIP: fine-tuned with a vast collection of coin images from CLIP using contrastive learning. It enhances feature extraction for coins, boosting image search accuracy. This model merges Visual Transformer (ViT) with CLIP's multimodal learning, optimized for numismatic applications.
☆23Updated 2 years ago
Alternatives and similar repositories for Coin-CLIP
Users that are interested in Coin-CLIP are comparing it to the libraries listed below
Sorting:
- Chinese CLIP models with SOTA performance.☆60Updated 2 years ago
- ☆57Updated last year
- Our 2nd-gen LMM☆34Updated last year
- 使用onnxruntime部署实时视频帧插值，包含C++和Python两个版本的程序☆28Updated last year
- Multimodal chatbot with computer vision capabilities integrated, our 1st-gen LMM☆101Updated last year
- 安卓手机部署DeepSeek-R1 蒸馏的1.5B模型☆23Updated 11 months ago
- convert paddleOCR to torchOCR, ppocr-v3,ppocr-v4, onnx, openvino☆33Updated 2 years ago
- A Simple MLLM Surpassed QwenVL-Max with OpenSource Data Only in 14B LLM.☆38Updated last year
- ☆187Updated last year
- segment anything model (SAM) infer by ncnn on Android mobile phone☆29Updated 2 years ago
- 陆续开源医疗行业的深度学习模型及数据集☆13Updated 4 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
- 用于学习GOT/Qwen/OnnxLLm☆53Updated last year
- 大模型API性能指标比较 - 深入分析TTFT、TPS等关键指标☆19Updated last year
- ICDAR 2024 Table OCR Model☆38Updated last week
- 研究GOT-OCR-项目落地加速，不限语言☆62Updated last year
- 使用ONNXRuntime部署鲁棒性视频抠图，包含C++和Python两种版本的程序☆46Updated 4 years ago
- 💡💡💡awesome compute vision app in gradio☆55Updated last year
- 读光中英文OCR onnx 版本模型使用 | Code for using the ONNX version of DuGuang OCR in both Chinese and English☆52Updated last month
- A light proxy solution for HuggingFace hub.☆49Updated 2 years ago
- Python scripts performing Open Vocabulary Object Detection using the YOLO-World model in ONNX.☆62Updated 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 3 years ago
- ☆10Updated 4 years ago
- 使用OpenCV部署眼睛凝视估计，包含C++和Python两个版本的程序，只依赖opencv库就可以运行，彻底摆脱对任何深度学习框架的依赖。☆16Updated 2 years ago
- DocTr++ in PaddlePaddle☆57Updated last year
- ☆42Updated 3 years ago
- segment anything（SAM） for CPP Inference☆31Updated last year
- 使用OpenCV部署CoupledTPS，包含了肖像矫正，不规则边界的图像矩形化，旋转图像矫正，三个模型。依然是包含C++和Python两个版本的程序☆20Updated last year
- A multimodal large-scale model, which performs close to the closed-source Qwen-VL-PLUS on many datasets and significantly surpasses the p…☆14Updated last year
- ncnn demo of (文档矫正)DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction☆44Updated 4 years ago