search

nisargptl / vehicle-recognition

This enables users to gather information about any vehicle and they can see the details in a matter of seconds. Snap a quick photo in the app and it will provide the details about the vehicle make, model, year, user ratings and starting retail price. In addition, it will provide this same information for the 2 closest competitors so a user can do some quick comparison shopping.
https://viris.herokuapp.com/
0 stars 1 forks source link

201801436_Challenges_Solutions #67

Closed khyatibhuva closed 3 years ago

khyatibhuva commented 3 years ago

Write your challenges you faced in this entire project and how to solved them.

vishal-2504 commented 3 years ago

I worked on the database part of this project.

  1. We found a dataset prepared by the Stanford University AI Lab consisting of the images for the cars, but the other important details of the cars except it’s names were not available anywhere. So, we manually searched for individual cars and created dataset.

  2. Then after, while creating firestore database in firebase, I faced difficulty in uploading dataset in the firebase. First of all, I converted my csv file into json file which basically converts the rows of dataset into javascript objects. I also faced problem in uploading json file in the database, For that I created another javascript file uploader.js and uploaded individual models by loading models from json file to uploader.js

  3. In image database, the images of required dimensions are not available. So, I resized the car images according to required dimensions.

khyatibhuva commented 3 years ago

Great Work!