Stars
🔥 基于MNN-llm的安卓手机部署大语言模型：Qwen1.5-0.5B-Chat
Official implementation of "OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association" in PyTorch.
This project uses a variety of advanced voiceprint recognition models such as EcapaTdnn, ResNetSE, ERes2Net, CAM++, etc. It is not excluded that more models will be supported in the future. At the …
LLM Finetuning with peft
[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型
Llama中文社区，实时汇总最新Llama学习资料，构建最好的中文Llama大模型开源生态，完全开源可商用
[ICCV 2023] Code base for Revisiting Scene Text Recognition: A Data Perspective
DataComp: In search of the next generation of multimodal datasets
🔎 🖼️ 🔥PyTorch Toolbox for Image Quality Assessment, including PSNR, SSIM, LPIPS, FID, NIQE, NRQM(Ma), MUSIQ, TOPIQ, NIMA, DBCNN, BRISQUE, PI and more...
Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, DeepSeek, Mixtral, Gemma, Phi, MiniCPM, Qwen-VL, MiniCPM-V, etc.) on Intel XPU (e.g., local PC with iGPU and NPU, discr…
A pure javascript QR code decoding library, accept Image File object, image url, image base64.
[CVPR2023] Blur Interpolation Transformer for Real-World Motion from Blur
python implementation of the paper "Spatially-Varying Blur Detection Based on Multiscale Fused and Sorted Transform Coefficients of Gradient Magnitudes" - cvpr 2017
Robust Python implementation for detecting blurry images using ROI estimation and DCT analysis.
基于transformer的ocr识别，在公章(印章识别, seal recognition）拓展应用
[CVPR 2024] Official implementation of "ViTamin: Designing Scalable Vision Models in the Vision-language Era"
A tool for parsing, editing, optimizing, and profiling ONNX models.
Harnessing 1.4M GPT4V-synthesized Data for A Lite Vision-Language Model
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
Building a quick conversation-based search demo with Lepton AI.
InstantID: Zero-shot Identity-Preserving Generation in Seconds 🔥
Industry leading face manipulation platform
Set of Python bindings to C++ libraries which provides full HW acceleration for video decoding, encoding and GPU-accelerated color space and pixel format conversions
Compare NVIDIA Video Codec SDK's, PyAV's, and OpenCV's performance on video decoding.
This may be the simplest implement of DDPM. You can directly run Main.py to train the UNet on CIFAR-10 dataset and see the amazing process of denoising.