Code Monkey home page Code Monkey logo

Comments (7)

souravrs999 avatar souravrs999 commented on May 24, 2024 1

Thank you and glad this repo was useful for someone, the model was actually trained on a mix of googles open image data-set and custom annoted datasets of normal images consisting of number plates for 2 wheeler's as well, because google's open image data-set only contained the images of cars and trucks but lacked any for smaller vehicles. This project was also made to be deployable on a Jetson nano attached to the dash cam of a car for Indian road condition's hence the custom datasets to include proper detection's for autorickshaw's, bikes and scooters as well. Hope this explanation was clear.

from license-plate-recognition.

souravrs999 avatar souravrs999 commented on May 24, 2024 1

Hi again, the complete dataset is uploaded to google driver i can share the link to you if it's ok, I did not convert the model to TensorRT yet i haven't got the time do it yet as i'm not working on it at the moment but i might in the future, The fps was under 10-12 ish when deployed on a nano i know it's not great but it's better than nothing.

Here's the link to the dataset as well as all the accompanying resources hope this helps.
https://drive.google.com/drive/folders/1dBYs9abE26ceC_boi75z7qh67KnKb-Pp?usp=sharing

from license-plate-recognition.

dzngo avatar dzngo commented on May 24, 2024 1

Thank you for your thoroughness.
Btw, actually, 10-12 FPS on Nano Jetson without converting into tensorRT is really good.

Looking forward to your future works.

from license-plate-recognition.

souravrs999 avatar souravrs999 commented on May 24, 2024 1

Thank you for your kind words and good luck on all your future endeavors.

from license-plate-recognition.

dzngo avatar dzngo commented on May 24, 2024

Thank you for your reply.

It would be grateful if you could share the datasets.
In terms of Nano Jetson, did you convert the yolov4-tiny to tensorRT engine plan? If yes, could you explain how you did that and what is the total FPS when the model is deployed on Nano Jetson?

Looking forward for your answer.

from license-plate-recognition.

ozett avatar ozett commented on May 24, 2024

i did not find the images for the dataset quickly,
so may i ask this as a question: is the recognition trained on some international license plates?
does it recognise license-plates for euopean countries?

thx

from license-plate-recognition.

souravrs999 avatar souravrs999 commented on May 24, 2024

i did not find the images for the dataset quickly, so may i ask this as a question: is the recognition trained on some international license plates? does it recognise license-plates for euopean countries?

thx

The model was trained on Google's open image dataset and it did contain license plates of multiple countries including eu

from license-plate-recognition.

Related Issues (1)

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.