hx358031364

llm-action

本项目旨在分享大模型相关技术原理以及实战经验。

yolov7

Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

segment-anything

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

ECCV2022-Papers-with-Code-Demo

收集 ECCV 最新的成果，包括论文、代码和demo视频等，欢迎大家推荐！

SparseR-CNN

[CVPR2021, PAMI2023] End-to-End Object Detection with Learnable Proposal

CVPR2024-Paper-Code-Interpretation

cvpr2024/cvpr2023/cvpr2022/cvpr2021/cvpr2020/cvpr2019/cvpr2018/cvpr2017 论文/代码/解读/直播合集，极市团队整理

CVPR2024-Papers-with-Code

CVPR 2024 论文和开源项目合集

CenterNet2

Two-stage CenterNet

google-access-helper

谷歌访问助手破解版

yolov5

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite

detectron2

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

yolov3

YOLOv3 in PyTorch > ONNX > CoreML > TFLite

torchvision-FasterRCNN

torchvision faster-rcnn例子修改版

yolov4-pytorch

这是一个YoloV4-pytorch的源码，可以用于训练自己的模型。

OD_dataset_conversion_scripts

object detection dataset conversion scripts

simple-faster-rcnn-pytorch

A simplified implemention of Faster R-CNN that replicate performance from origin paper

ResNeXt-PyTorch

meta-learning-lstm-pytorch

pytorch implementation of Optimization as a Model for Few-shot Learning

fewshot-egnn

Siamese-Networks

Few Shot Learning by Siamese Networks, using Keras.

LearningToCompare-Tensorflow

Tensorflow implementation for paper: Learning to Compare: Relation Network for Few-Shot Learning.

Image-matching-and-ranging-based-on-binocular-stereo-vision

双目立体视觉是计算机视觉范畴的核心之一，它利用双目相机来获得目标物体的图像，经过物体图像处理 之后得到目标物体所在场景环境的三维信息，最终实现非接触条件下测距，简单便捷。本次毕业设计主要内容为研究 基于双目立体视觉平台上的图像匹配以及目标物体的距离测量技术，图像特征提取部分研究了 SIFT 算法和 SURF 算 法，特征匹配部分研究了 BF 法和 FLANN 法，距离测量研究主要通过视差深度的计算，结合视觉坐标系的转换实现 三维位置的定位与测量。结合维视双目立体视觉测量平台 MV-VS220，通过 Python+OpenCV 设计实现一个具备图像 采集、图像匹配以及距离测量等功能的原型演示系统。系统可实现对关键环节的过程与结果的演示，以及不同算法的 性能比较。系统测试表明，所开发的原型演示系统从界面、功能与性能方面均达到了设计的要求。

Feature-Matching

identification of reference surface in static frames or real-time frame from the computed descriptors using CV

feature-matching-example

Example of real-time feature point detection and matching (AKAZE, ORB)

OpenCV2-Python-Tutorials

This repo contains tutorials on OpenCV-Python library using new cv2 interface

imgaug

Image augmentation for machine learning experiments.

Keras-FasterRCNN

keras implementation of Faster R-CNN

CornerNet

fire-detection-cnn

real-time fire detection in video imagery using a convolutional neural network (deep learning) - from our ICIP 2018 paper (Dunnings / Breckon) + ICMLA 2019 paper (Samarth / Bhowmik / Breckon)

tensorflow_models_learning

tensorflow GoogleNet inception V1 V2 V3 V4