In this section, we will code the strategy that we defined prior (the code file is available as Gender classification.ipynb in GitHub):
- Download the dataset:
$ wget https://d1p17r2m4rzlbo.cloudfront.net/wp-content/uploads/2017/04/a943287.csv
- Load the dataset and inspect its content:
import pandas as pd, numpy as npfrom skimage import io# Location of file is /content/a943287.csv# be sure to change to location of downloaded file on your machinedata = pd.read_csv('/content/a943287.csv')data.head()
A sample of some of the key fields in the dataset is as follows:
- Fetch 1,000 male images and 1,000 female images from the URL ...