SkillPedia Skills Encyclopedia
中文 EN

yolo_researchpositive666/yolo_research

A PyTorch-based YOLO object detection project covering the full chain from accuracy evaluation and speed benchmarking to…

No ratings yet Rate this skill
Stars668
Forks135
Watchers668
Open Issues12

InstallOne-line install

Unconfirmed

Whether this repository follows the Agent Skills spec (that is, whether it contains a SKILL.md) has not been verified yet. Until that is settled, clone it and use what you need:

git clone https://github.com/positive666/yolo_research.git

OverviewOverview

Key Features

A PyTorch-based YOLO object detection project covering the full chain from accuracy evaluation and speed benchmarking to model export, helping developers quickly validate and deploy detection models. Key capabilities include: 1. Accuracy: reports mAP and other accuracy metrics under single-model single-scale settings for side-by-side comparison of YOLOv5/YOLOv7/YOLOv8 variants and attention-enhanced detectors; 2. Speed: averages inference time over 100 images to quantify frame rate and latency on target hardware, supporting model selection and deployment decisions; 3. Export: exports trained models into deployment formats, bridging training and inference engines such as DeepStream; 4. Architecture Extension: integrates SwinTransformer, attention mechanisms and custom network structures so modules can be swapped or inserted into YOLO backbones for comparative experiments.

Use Cases

object detection model selection and accuracy comparison, inference performance stress testing and hardware compatibility evaluation, exporting trained models into DeepStream video analytics pipelines, ablation studies on attention mechanisms and custom backbones.

Target Roles

AI / Algorithm Engineer, Data Analyst / Data Engineer, Hardware / Embedded Engineer, Test / QA Engineer.

TopicsTopics

RatingUser ratings

Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.

Rate this skill

Fill it in to be included in the per-role averages below.

One vote per IP,and it cannot be changed after submitting, so choose carefully the first time. No account is collected and no sign-in is required.

RepositoryRepository

Skill ID1832
Data sourceGitHub
Repositorypositive666/yolo_research
CategoryAI & Algorithms / Computer Vision & Object Detection
Primary languagePython
LicenseGNU General Public License v3.0
Default branchmaster
GitHub repository ID342215698
Node IDMDEwOlJlcG9zaXRvcnkzNDIyMTU2OTg=
Rank#1022 (position within the source ranking)
Site-wide popularity rank#1188 (computed live from Stars, across all 5845 entries)

GrowthStar / Fork growth

One snapshot per day, tracking how Stars and Forks changed

02004006008002026-09-222026-10-112026-09-22 · 6672026-10-11 · 668
  • Now668
  • Previous point · 09-22 667
  • vs previous point +1
  • 2 data points 19 days
0501001502026-09-222026-10-112026-09-22 · 1352026-10-11 · 135
  • Now135
  • Previous point · 09-22 135
  • vs previous point ±0
  • 2 data points 19 days

TimelineTimeline

Repository created2021-02-25 11:02:172021-02-25
Data last updated2026-10-26 12:07:4124 days ago
Last commit2026-04-27 04:06:376 months ago

CommitLatest commit

Version [v2.0.0] committed by positive666. Update Category: Bug Fixes & Stability Improvements. Commit details: fix bug. This update resolves known runtime errors and enhances system reliability.

f5795f2 v2.0.0 positive666 2023-06-25