blog.csdn

HOG+SVM行人检测实战：从源码到模型训练全流程

该技术方案在智能监控、自动驾驶和客流统计等场景中具有重要工程价值。 本文基于一份完整的C++源码，详细拆解从负样本裁剪、HOG特征提取、SVM训练到hard negative挖掘的每一步，并分享编译避坑与Python调参技巧，帮助读者快速跑通行人检测项目。
blog.csdn

Python文本情感分析实战：从爬虫、情感词典到机器学习分类的完整 ...

本内容遵循CC 4.0 BY-SA版权协议 简介：一份面向高校计算机/人工智能相关专业学生的情感分析课程设计源码包，基于情感词典 ...
BIOENGINEER

Deep Learning Learns to Tell Rice Varieties Apart, One Grain at a Time

Researchers in Türkiye combined transfer learning with MobileNetV2, Xception, and classical classifiers to classify five rice ...

What is Scaling For? Methods That Require Standardization/Normalization and Those That Do Not

Up until the last article, we covered how to convert categorical variables into numbers. This time, we will look at scaling, ...
huggingface

Multi-view SVM reward models (scan_object)

A dense process reward for RL fine-tuning, following Learning Process Rewards via Success Visitation Matching (SVM): a discriminator f(s, a) trained to tell decision ...
Science

Metabolomic aging and mortality clocks based on ensemble learning identify systemic aging ...

Plasma metabolomic profiling across the human life span yields two aging metrics linked to chronic disease and mortality.
GitHub

Day 11 — SVM / 360° Fisheye Demo (CVAT, local)

Practice tasks for the Day 11 "SVM / 360° External Cameras" lecture (fisheye, surround-view, camera-specific QA). Built from svm360-day11-theory.pdf.
GitHub

Fruit Classification using Machine Learning

This project uses a fruit dataset containing numerical measurements of different fruits. The features include mass, width, height, and color score. The dataset is processed and divided into training ...

[Eliminate 4,100 Hours of Annual Emergency Response] Building a Pipeline for Automatic ...

What is the most exhausting factor for maintenance teams in manufacturing facilities?It is the sudden line stoppages (major breakdowns), late-night emergency calls, and the 'scramble maintenance' ...