ultralytics/yolov5

iOS iDetection Speed Table

Open

#1276 opened on Nov 3, 2020

View on GitHub
 (30 comments) (14 reactions) (1 assignee)Python (57,369 stars) (17,479 forks)batch import
documentationenhancementhelp wanted

Description

🚀 Feature

We'd like to create an iDetection Speed Table for each year's iPhone release, going back as far as iDetection will run, which may be around iPhone 5 or 6. Crowd-sourcing the table will help show real-world performance of the models on various hardware.

If you have an iOS device, you can contribute by downloading iDetection, testing your speeds, and then uploading your results here. We try to test near 100% battery at room temperature (about 25°C), and record the speed after about 10 seconds of inference for each model.

Please help by uploading your results! Thank you!!

iDetection v7.8 Inference Speeds

  Year ASIC-process ANE(TOPS) YOLOv5s(ms) YOLOv5m(ms) YOLOv5l(ms) YOLOv5x(ms)
iPhone 6 2014 A8-20nm - 90 180 350 500
iPhone 6s 2015 A9-16nm - 148 216 304 475
iPhone 7 2016 A10-16nm - 94.7 140.7 216.7 289.8
iPhone 8/X 2017 A11-10nm 0.6 - - - -
iPhone XR/XS 2018 A12-7nm 5.0 22.3 25.8 43.2 57.7
iPhone 11 2019 A13-7nm 6.0 17.4 21.3 27.8 41.2
iPhone 12 2020 A14-5nm 11.0 14.3 16.5 21.0 28.8
iPhone 13 2021 A15-5nm 15.8

*CoreML models exported as FP8 320x192 with release v3.1 *Measured with iDetection v7.8 at 100% battery at 25°C. Average speed after 10 seconds recorded.

Contributor guide

Tech stack
pythonios
Domain
mobileperformance
Issue type
feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
2
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
under 1 hour
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
clear
Prerequisites
iOS deviceiDetection app
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
90
Research direction
To contribute, download iDetection from the App Store, run it on your iPhone, and record inference speeds for each model after 10 seconds. Then, update the table in the issue body with your device's year, ASIC, ANE TOPS, and measured speeds for YOLOv5s/m/l/x. Follow the existing format and ensure battery is near 100% and temperature around 25°C.