average-precision 开源项目推荐（28 个）

rafaelpadilla /Object-Detection-Metrics

Most popular metrics used to evaluate object detection algorithms.

Cartucho /mAP

mean Average Precision -此代码评估神经网络在对象识别方面的性能。

rafaelpadilla /review_object_detection_metrics

对象检测收件箱。14个对象检测指标：平均平均精度（mAP）、平均召回率（AR）、时空管平均精度（STT-AP）。该项目支持不同的边界框格式，例如COCO、PascAL、Imagenet等。

laclouis5 /globox

读取和转换对象检测数据集（COCO、YOLO、PascalVOC、LabelMe、CVAT、OpenImage等）的包并使用COCO和PascalVOC指标对其进行评估。

ZFTurbo /Mean-Average-Precision-for-Boxes

Function to calculate mAP for set of detected boxes and annotated boxes.

zzhanghub /eval-co-sod

PyTorch-Based Evaluation Tool for Co-Saliency Detection

elias-ramzi /ROADMAP

This repository contains the official implementation of the NeurIPS'21 paper, ROADMAP: Robust and Decomposable Average Precision for Image Retrieval.

CAMMA-public /ivtmetrics

A Python evaluation metrics package for surgical action triplet recognition

EMalagoli92 /OD-Metrics

Python library for Object Detection metrics.

Mr-TalhaIlyas /Evaluation-Metrics-Package-Tensorflow-PyTorch-Keras

ML/CNN Evaluation Metrics Package

shreejalt /mAP-calculator

A simple script to calculate the mAP using PascalVOC2012 and COCO standards for object detection

Wb-az /yolov8-disease-detection-agriculture

YOLOV8 - Object detection

KentaItakura /how-to-calculate-average-precision-for-object-detection

PR曲線を用いた平均適合率の計算の方法についての説明と、実装による理解の確認を行います。

sichkar-valentyn /What-is-mAP-for-Objects-Detection-tasks-

Understanding of use of mAP as a metric for Objects Detection problems

atharvaa45 /Predictive-Analytics-Student-Retention-Fairness-Aware-Intervention

End-to-end predictive analytics pipeline for student retention using imbalanced academic data, stacked ML models, recall-optimized decision thresholds, and fairness-aware evaluation with cost–benefit analysis.

woov2 /Manager_Matching_Prediction_Industry_Academia_Linkage_Contest

[공모전] 제1회 산학연계 공모전 - 고객과 가사도우미 매칭 성공 여부 예측 AI 모델 개발

saha350 /Uber_Traffic_Data_Analysis

In this Power Bi project, all the data has been compared using different shifts and the delayed time. Here the range of the upper bound is also analyzed where the maximum upper bound is predicted in the morning shift compared to mid-day and evening shift. The delay time in morning (A.M.) and Evening (P.M.) ranges have also been predicted.

zhousrhhh /Credit_Rating_Modeling

Built various machine learning models for banks to develop effective credit rating

karthikvadlamani /revolut-fraudsters-detection

Performed feature engineering, cross-validation (5 fold) on baseline and cost-sensitive (accounting for class imbalance) Decision trees and Logistic Regression models and compared performance. Used appropriate performance metrics i.e., AUC ROC, Average Precision and Balanced Accuracy. Outperformed baseline model.

Sliverk /hybridAveragePrecision

This is a novel average precision calculation named hybrid N-point interpolation method to eliminate the average precision distortion in KITTI 3D Object Detection Benchmark.