territoryLiu

territoryLiu's Stars

• caiyuanhao1998/PNGAN

  "Learning to Generate Realistic Noisy Images via Pixel-level Noise-aware Adversarial Training" (NeurIPS 2021)

  Language:Python13622

• google-research/tuning_playbook

  A playbook for systematically maximizing the performance of deep learning models.

  27.7k2.3k

• schrodingercatss/tuning_playbook_zh_cn

  一本系统地教你将深度学习模型的性能最大化的战术手册。

  2.7k243

• raymond1123/Flash-Attention

  Language:Cuda25

• raymond1123/hgemm

  Language:Cuda29

• zhahoi/Nanodet-YoloV8-Pose-MeterReader

  使用Nanodet+YoloV8-Pose实现指针仪表的实时检测、高精度读数识别（借助ncnn框架）

  Language:C++532

• Keylost/jetson-ffmpeg

  ffmpeg support on nvidia jetson

  Language:Makefile9730

• hiyouga/LLaMA-Factory

  Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

  Language:Python37.4k4.6k

• Geekgineer/YOLOs-CPP

  A high-performance C++ headers for real-time object detection using YOLO models, leveraging ONNX Runtime and OpenCV for seamless integration. Supports multiple YOLO versions (v5, v7, v8, v10, v11) with optimized inference on CPU and GPU. Includes sample code, scripts for image, video, and live camera inference, and tools for quantization.

  Language:C++35134

• harleyszhang/cv_note

  记录cv算法工程师的成长之路，分享计算机视觉和模型压缩部署技术栈笔记。https://harleyszhang.github.io/cv_note/

  Language:Python2.5k383

• harleyszhang/lite_llama

  A light llama-like llm inference framework based on the triton kernel.

  Language:Python755

• superlinear-ai/raglite

  🥤 RAGLite is a Python toolkit for Retrieval-Augmented Generation (RAG) with PostgreSQL or SQLite

  Language:Python65749

• Nutlope/llama-ocr

  Document to Markdown OCR library with Llama 3.2 vision

  Language:TypeScript2k165

• rockchip-linux/mpp

  Media Process Platform (MPP) module

  Language:C641181

• SuperMedIntel/Medical-SAM2

  Medical SAM 2: Segment Medical Images As Video Via Segment Anything Model 2

  Language:Python53267

• sagieppel/fine-tune-train_segment_anything_2_in_60_lines_of_code

  The repository provides code for training/fine tune the Meta Segment Anything Model 2 (SAM 2)

  Language:Jupyter Notebook16122

• SuperMedIntel/Medical-SAM-Adapter

  Adapting Segment Anything Model for Medical Image Segmentation

  Language:Python1k92

• facebookresearch/sam2

  The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

  Language:Jupyter Notebook13.5k1.3k

• babysor/MockingBird

  🚀AI拟声: 5秒内克隆您的声音并生成任意语音内容 Clone a voice in 5 seconds to generate arbitrary speech in real-time

  Language:Python35.6k5.2k

• chaofengc/IQA-PyTorch

  👁️ 🖼️ 🔥PyTorch Toolbox for Image Quality Assessment, including PSNR, SSIM, LPIPS, FID, NIQE, NRQM(Ma), MUSIQ, TOPIQ, NIMA, DBCNN, BRISQUE, PI and more...

  Language:Python2.1k179

• TencentYoutuResearch/CrowdCounting-P2PNet

  The official codes for the ICCV2021 Oral presentation "Rethinking Counting and Localization in Crowds: A Purely Point-Based Framework"

  Language:Python436115

• NVIDIA/Deep-Learning-Accelerator-SW

  NVIDIA DLA-SW, the recipes and tools for running deep learning workloads on NVIDIA DLA cores for inference applications.

  Language:Python18415

• huangzongmou/Yolov8-Hisi

  yolov8在hisi3536a推理

  Language:C++8

• KimSinjeong/keypt2subpx

  Implementation of "Learning to Make Keypoints Sub-Pixel Accurate" (ECCV 2024).

  Language:Python1188

• dusty-nv/jetson-utils

  C++/CUDA/Python multimedia utilities for NVIDIA Jetson

  Language:C++759298

• wangzyon/pyInfer

  async inference for machine learning model

  Language:Python266

• BaofengZan/hard_decode_trt-windows

  https://github.com/shouxieai/hard_decode_trt windows编译版本

  Language:C++132

• shouxieai/hard_decode_trt

  Yolov5 inference on NVDec hardware decoder

  Language:C++8728

• BBuf/how-to-optim-algorithm-in-cuda

  how to optimize some algorithm in cuda.

  Language:Cuda1.8k150

• CodingHanYa/workspace

  workspace是基于C++11的轻量级异步执行框架，支持：通用任务异步并发执行、优先级任务调度、自适应动态线程池、高效静态线程池、异常处理机制等。

  Language:C++1.1k158