Giter VIP home page Giter VIP logo

ai_hackaton_2022's Introduction

AI HACKATON


BRAIN NTNU x Microsoft x HUB Ocean


Objektdeteksjon av korallrev ved hjelp av Sentinel-satelittbilder

av Martin Johannes Nilsen, Ole Jonas Liahagen, Zaim Imran og Salar Adel

Introduksjon

Hva har blitt gjort:

  • Hentet bilder fra Planetary HUB
  • Klassifisering av data med Azure ML assisted labeling
  • Eksporter som COCO, oversett til YOLO
  • Bilder og labels på riktig format
  • Nedskalering av bilder, 343px ganske spesiell oppløsning så nå oppløsning på 320px (32-gangen for kernel av 32px i YOLO)
  • Trening av YOLOv5 på denne

Hvordan trene YOLOv5-nettverket

Eksempel på trening:

python train.py --img 320 --batch 16 --epochs 80 --data dataset.yaml --weights yolov5s.pt --optimizer Adam --cache
  • img: define input image size
  • batch: determine batch size
  • epochs: define the number of training epochs.
  • data: Our dataset locaiton is saved in the dataset.location
  • weights: specify a path to weights to start transfer learning from. Here we choose the generic COCO pretrained checkpoint.
  • optimizer: Select optimizer {SGD, Adam, AdamW}
  • cache: cache images for faster training

Detektering med trente vekter

python detect.py --weights runs/train/exp/weights/best.pt --img 320 --conf 0.1 --source ../datasets/coral/images/train2022 --data data/dataset.yaml
  • weights: specify path of weights as .pt-file
  • img: define input image size
  • conf: confidence needed for classification
  • source: define path to test images

Har i tillegg brukt noen av disse argumentene:

  • --hide-conf
  • --hide-labels
  • --iou-thres 0.2
  • --line-thickness 1

Full liste er å finne nederst i detect.py

ai_hackaton_2022's People

Contributors

martinjohannesnilsen avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.