QJSQJS's repositories
MHFormer_ResiDual
Improving the pose estimation performance of 3D people in MHFormer using the ResiDual method.
pointops_cuda_windows
pointops_cuda for windows
objectdetection_script
一些关于目标检测的脚本的改进思路代码，详细请看readme.md
smoothly-vslam
VSLAM开源基础教程，各章节练习代码
Alpaca-CoT
We unified the interfaces of instruction-tuning data (e.g., CoT data), multiple LLMs and parameter-efficient methods (e.g., lora, p-tuning) together for easy use. We welcome open-source enthusiasts to initiate any meaningful PR on this repo and integrate as many LLM related technologies as possible. 我们打造了方便研究人员上手和使用大模型等微调平台，我们欢迎开源爱好者发起任何有意义的pr！
annotate_images
Automatic labeling ：使用YOLOv8自动标注数据集
Awesome-Monocular-3D-detection
Awesome Monocular 3D detection
Awesome-Transformer-Attention
An ultimately comprehensive paper list of Vision Transformer/Attention, including papers, codes, and related websites
DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
DINOv2ForRadiology
Evaluating DINOv2 for Radiology
FastSAM
Fast Segment Anything
Financial-Knowledge-Graphs
小型金融知识图谱构建流程
FinGLM
FinGLM: 致力于构建一个开放的、公益的、持久的金融大模型项目，利用开源开放来促进「AI+金融」。
flash-attention
Fast and memory-efficient exact attention
KnowledgeGraph
knowledge graph知识图谱,从零开始构建知识图谱
model-metrics-plot
🔨🔨🔨(mmplot)used to draw graphs of multiple index parameters such as algorithm accuracy and speed of multiple deep learning models.
NExT-Chat
The code of the paper "NExT-Chat: An LMM for Chat, Detection and Segmentation".
pytorch_geometric
Graph Neural Network Library for PyTorch
SAN
Pytorch implementation of NIPS'23 paper: Adaptive Normalization for Non-stationary Time Series Forecasting: A Temporal Slice Perspective
small-object-detection-benchmark
icip2022 paper: sahi benchmark on visdrone and xview datasets using fcos, vfnet and tood detectors
SwinTransformer-YOLOv5
一个修改YOLOv5以使用SwinTransformer模块的代码仓库。A repository that modifies YOLOv5 to use various SwinTransformer blocks.
Tabular-LLM
本项目旨在收集开源的表格智能任务数据集（比如表格问答、表格-文本生成等），将原始数据整理为指令微调格式的数据并微调LLM，进而增强LLM对于表格数据的理解，最终构建出专门面向表格智能任务的大型语言模型。
X-AnyLabeling
Effortless data labeling with AI support from Segment Anything and other awesome models.
YOLOv5-6D-Pose
6-DoF Pose estimation based on the YOLOv5 framework. Specific focus on instruments in X-ray applications
YOLOv8-3D
YOLOv8-3D is a LowCode, Simple 2D and 3D Bounding Box Object Detection and Tracking , Python 3.10