Skip to content

this code shows the train and test of a YOLOV5 convolutional neural network for detection of electronics components

Notifications You must be signed in to change notification settings

talisma-cassoma/pcb-components-detection-recognition

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

35 Commits
 
 
 
 
 
 

Repository files navigation

pcb component detection/recognition

This code shows the train and test of a YOLOV5 convolutional neural network for recognition of electronics components

see the model working on video: here

🔥 SETUP

download the folder and upload to your google drive put in a dir named /Real_PCB/Databset/ :

here it's the dataset originaly created by Animeshkumar Nayak(available on Kaggle) with some improvements that i made in roboflow

This is how should look the projet struture :

MyDrive/
└── Real_PCB/
    ├── Dataset/
    │   └── pcb_data/
    │       ├── data.yaml     
    │       ├── test/
    │       ├── valid/
    │       └── train/
    │   
    └── yolov5/

THE TRAIN

I chose to train on colab cause i havent a powerfull GPU as colab invidia does and its free :)

The train process is all commented

THE TEST

To test the models you only need the results. its also commented

yolov5 allows you to test the model using videos images even your web camera if you setup it your machine

ABOUT THE RESULTS

(see more results here: here )


   

1643468008461.mp4

About

this code shows the train and test of a YOLOV5 convolutional neural network for detection of electronics components

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published