Pinned Repositories
AI-on-Board
Examples of AI model running on the board, such as horizon/rockchip and so on.
mmyolo
OpenMMLab YOLO series toolbox and benchmark
ncnn-examples
Learning ncnn with some examples
np-map
A simple tool for calculating object detection map
Stable-Diffusion-TensorRT
Stable Diffusion in TensorRT 8.5+
TensorRT2ONNX
A tool convert TensorRT engine/plan to a fake onnx
TensorRT8-Python-Wheels
TensorRT8 Python Wheels for x86
yolov7
Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
yolov8
YOLOv8 🚀 in PyTorch > ONNX > CoreML > TFLite
YOLOv8-TensorRT
YOLOv8 using TensorRT accelerate !
triple-Mu's Repositories
triple-Mu/YOLOv8-TensorRT
YOLOv8 using TensorRT accelerate !
triple-Mu/yolov8
YOLOv8 🚀 in PyTorch > ONNX > CoreML > TFLite
triple-Mu/mmyolo
OpenMMLab YOLO series toolbox and benchmark
triple-Mu/yolov5
YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
triple-Mu/FastDeploy
⚡️An Easy-to-use and Fast Deep Learning Model Deployment Toolkit for Cloud and Edge. Including Vision, Text, Audio and Video 20+ main stream scenarios and 150+ SOTA models with end-to-end optimization and multi-platform multi-framework support.
triple-Mu/mmagic
OpenMMLab Multimodal Advanced, Generative, and Intelligent Creation Toolbox. Unlock the magic 🪄: Generative-AI (AIGC), easy-to-use APIs, awsome model zoo, diffusion models, for text-to-image generation, image/video restoration/enhancement, etc.
triple-Mu/mmdetection
OpenMMLab Detection Toolbox and Benchmark
triple-Mu/ncnn
ncnn is a high-performance neural network inference framework optimized for the mobile platform
triple-Mu/PaddleDetection
Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.
triple-Mu/PaddleNLP
👑 Easy-to-use and powerful NLP library with 🤗 Awesome model zoo, supporting wide-range of NLP tasks from research to industrial applications, including 🗂Text Classification, 🔍 Neural Search, ❓ Question Answering, ℹ️ Information Extraction, 📄 Document Intelligence, 💌 Sentiment Analysis and 🖼 Diffusion AIGC system etc.
triple-Mu/PaddleOCR
Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)
triple-Mu/The-supplemented-files-of-Small-Insulator-Defects-Detection-for-UAV-assisted-Power-IoVT-
The part data of the proposed Insulator super-resolution detection dataset (ISDD) in "Small Insulator Defects Detection based on Multi-scale Feature Interaction Transformer for UAV-assisted Power IoVT"
triple-Mu/YOLOv6
YOLOv6: a single-stage object detection framework dedicated to industrial applications.
triple-Mu/yolov9
Implementation of paper - YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information
triple-Mu/baby-llama2-chinese
用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库;24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.
triple-Mu/lm-evaluation-harness
A framework for few-shot evaluation of autoregressive language models.
triple-Mu/Megatron-LM
Ongoing research training transformer models at scale
triple-Mu/mmcv
OpenMMLab Computer Vision Foundation
triple-Mu/mmengine
OpenMMLab Foundational Library for Training Deep Learning Models
triple-Mu/mmpose
OpenMMLab Pose Estimation Toolbox and Benchmark.
triple-Mu/mmpretrain
OpenMMLab Image Classification Toolbox and Benchmark
triple-Mu/mmrotate
OpenMMLab Rotated Object Detection Toolbox and Benchmark
triple-Mu/mnn-llm
llm deploy project based mnn.
triple-Mu/opencompass
OpenCompass is an LLM evaluation platform, supporting a wide range of models (InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.
triple-Mu/optimum-benchmark
A unified multi-backend utility for benchmarking Transformers and Diffusers with full support of Optimum's hardware optimizations & quantization schemes.
triple-Mu/PaddleGAN
PaddlePaddle GAN library, including lots of interesting applications like First-Order motion transfer, Wav2Lip, picture repair, image editing, photo2cartoon, image style transfer, GPEN, and so on.
triple-Mu/PaddleSlim
PaddleSlim is an open-source library for deep model compression and architecture search.
triple-Mu/super-gradients
Easily train or fine-tune SOTA computer vision models with one open source training library. The home of Yolo-NAS.
triple-Mu/vllm_official
A high-throughput and memory-efficient inference and serving engine for LLMs
triple-Mu/xformers
Hackable and optimized Transformers building blocks, supporting a composable construction.