Learn practical skills, build real-world projects, and advance your career
Updated 4 years ago
In this project, I have made an attempt to classify book genres according to their book cover pages using the FastAI framework and popular transfer learning models such as resnet34, resnet50 and resnet101. All these model architectures have been explored and analysed in detail to arrive at the best model for our data.
Data for this has been scraped from Google Images using :
urls=Array.from(document.querySelectorAll('.rg_i')).map(el=> el.hasAttribute('data-src')?el.getAttribute('data-src'):el.getAttribute('data-iurl'));
window.open('data:text/csv;charset=utf-8,' + escape(urls.join('\n')));
Go to the Google Images page from you want to download images from, and type the above code on 'console' inside the 'Inspect' available in Google Chrome.
This will get you the urls for all the images downloaded in a .csv file.
Additionally, I have used My Drive to save my data for this project. You can choose any path to do so.
#make sure fastai is up to date
!curl -s https://course.fast.ai/setup/colab | bashUpdating fastai...
Done.
#read in standard data science libs
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt#import google drive package
from google.colab import drive# connect workbook to google drive folder to access images
drive.mount('/content/gdrive')Go to this URL in a browser: https://accounts.google.com/o/oauth2/auth?client_id=947318989803-6bn6qk8qdgf4n4g3pfee6491hc0brc4i.apps.googleusercontent.com&redirect_uri=urn%3aietf%3awg%3aoauth%3a2.0%3aoob&response_type=code&scope=email%20https%3a%2f%2fwww.googleapis.com%2fauth%2fdocs.test%20https%3a%2f%2fwww.googleapis.com%2fauth%2fdrive%20https%3a%2f%2fwww.googleapis.com%2fauth%2fdrive.photos.readonly%20https%3a%2f%2fwww.googleapis.com%2fauth%2fpeopleapi.readonly
Enter your authorization code:
··········
Mounted at /content/gdrive