How to make images as an datasets for keras python

Question

I currently have images in my local laptop and would like to transform them into datasets in order to load in for keras python. Is there any solutions for me to do that?

Answer 1

You can use ImageDataGenerator to load the images.

        train_datagen = ImageDataGenerator(
        rescale=1./255,
        shear_range=0.2,
        zoom_range=0.2,
        horizontal_flip=True)

        train_generator = train_datagen.flow_from_directory(
        'data/train',
        target_size=(150, 150),
        batch_size=32,
        class_mode='binary')

https://keras.io/preprocessing/image/

Answer 2

In this link, you can find several ways of loading your images from your directory using Python. A simple way also is the following:

import numpy as np
import cv2
import os

instances = []

# Load in the images
for filepath in os.listdir('images/'):
   instances.append(cv2.imread('images/{0}'.format(filepath),0))

print(type(instances[0]))

Not sure if it is the most efficient though.