How Should I customize data for Custom Dataset Training?

[PIjarihd]

I am trying to train the custom dataset. However, I am quite confused with the process. What exact changes should I made? Can you please guide me step wise? I studied #62. #8 and #5 , however I still could not figure out how should I prepare the data? Do I need to make the folders exactly like this?

Which code should I run to downscale the image? How should I prepare caches?
Please guide me or provide me some tutorial link. Thanks in advance.

[huchi00057]

Same problem

[Gooda97]

I am trying to train the custom dataset. However, I am quite confused with the process. What exact changes should I made? Can you please guide me step wise? I studied #62. #8 and #5 , however I still could not figure out how should I prepare the data? Do I need to make the folders exactly like this? Which code should I run to downscale the image? How should I prepare caches? Please guide me or provide me some tutorial link. Thanks in advance.

lr_images_path = r'C:\Users\dell\Downloads\super_resolution\input'
hr_images_path = r'C:\Users\dell\Downloads\super_resolution\output'

file_paths_1 = sorted(sorted(glob.glob(os.path.join(lr_images_path, ".png"))))
file_paths_2 = sorted(sorted(glob.glob(os.path.join(hr_images_path, ".png"))))

lr_dataset = tf.data.Dataset.from_tensor_slices(file_paths_1)
hr_dataset = tf.data.Dataset.from_tensor_slices(file_paths_2)

def load_and_preprocess_image(file_path):
image = tf.io.read_file(file_path)

image = tf.image.decode_png(image, channels=3)

image = tf.image.convert_image_dtype(image, tf.float32)

return image

lr_dataset = lr_dataset.map(load_and_preprocess_image)
hr_dataset = hr_dataset.map(load_and_preprocess_image)

combined_dataset = tf.data.Dataset.zip((lr_dataset, hr_dataset))

batched_dataset = combined_dataset.batch(1)

prefetched_dataset = batched_dataset.prefetch(tf.data.experimental.AUTOTUNE)

DATASET_SIZE= len(prefetched_dataset)

train_size = int(0.97 * DATASET_SIZE)
test_size = DATASET_SIZE - train_size

train_dataset = prefetched_dataset.take(train_size)
test_dataset = prefetched_dataset.skip(train_size)