How can I read images in Kaggle with Python?

Question

I am working in a analysis of data mining. I'm working with images from Kaggle, in a notebook in it. I have the root of this images given by .jpeg.

How can I read them? Then, I have to use this function tf.keras.preprocessing to get the variable and use it in a CNN model in Keras.

Thanks a lot!

Answer 1

As asked using keras, we can use :

tf.keras.utils.image_dataset_from_directory(
    directory,
    labels="inferred",
    label_mode="int",
    class_names=None,
    color_mode="rgb",
    batch_size=32,
    image_size=(256, 256),
    shuffle=True,
    seed=None,
    validation_split=None,
    subset=None,
    interpolation="bilinear",
    follow_links=False,
    crop_to_aspect_ratio=False,
    **kwargs
)

However, if we want to have a look at some pictures first, we can use the PIL library to display it directly in the notebook like so :

from PIL import Image

img = Image.open('path/image.jpg')
img

This nice tutorial might help you even better (at least it helped me a lot).