[FIXED] Resize all images in a subdirectory

Issue

I have a directory named TRAIN, and it has 37 subdirectoris which contains images of different size, I wanted to load those images with TensorFlow's ImageDataGenerator, but it needs images of same size. I want to add padding to those images to resize them.

  tf.image.resize_with_crop_or_pad(
    image, target_height, target_width
)

I found this above code on internet but I don't know how to use it.

Solution

Resize the images from the directories using tf.keras.preprocessing.image_dataset_from_directory. Mention the required image size in image_size=(img_height, img_width). Default image_size will be (256,256) Find the below sample code

import tensorflow as tf
train_ds = tf.keras.preprocessing.image_dataset_from_directory(
  data_dir,
  validation_split=0.2,
  subset="training",
  seed=123,
  image_size=(img_height, img_width),
  batch_size=batch_size)

Answered By - TFer