Hands-On Transfer Learning with Python

Building our dataset

While we can use all 25,000 images and build some nice models on them, if you remember, our problem objective includes the added constraint of having a small number of images per category. Let's build our own dataset for this purpose. You can refer to the Datasets Builder.ipynb Jupyter Notebook in case you want to run the examples yourself.

To start with, we load up the following dependencies, including a utility module called utils, which is available in the utils.py file present in the code files for this chapter. This is mainly used to get a visual progress bar when we copy images into new folders:

import glob 
import numpy as np 
import os 
import shutil 
from utils import log_progress 
 
np.random.seed(42) 

Let's now load ...