Datasets

from hypergen import dataset

# Load all images from a folder
ds = dataset.load("./my_training_images")
print(f"Loaded {len(ds)} images")

my_images/
  photo1.jpg
  photo2.png
  photo3.webp
  ...

my_images/
  photo1.jpg
  photo1.txt        <- "A beautiful sunset over the ocean"
  photo2.jpg
  photo2.txt        <- "A person walking in a forest"
  photo3.png
  photo3.txt        <- "Close-up of a flower"
  ...

from hypergen import dataset

ds = dataset.load("./my_images")

ds = dataset.load(
    "./my_images",
    extensions=[".jpg", ".png"]  # Only load JPG and PNG files
)

# Get dataset size
print(f"Dataset has {len(ds)} images")

# Iterate over items
for image, caption in ds:
    print(f"Image size: {image.size}")
    print(f"Caption: {caption}")
    break  # Just show first item

for batch in ds.batch(batch_size=4):
    print(f"Batch has {len(batch)} items")
    for image, caption in batch:
        # Process each item in the batch
        pass

# Get specific item by index
image, caption = ds[0]

# Check if captions are available
if caption is not None:
    print(f"Has caption: {caption}")
else:
    print("No caption for this image")

# Image paths
print(ds.image_paths)  # List of Path objects

# Captions (may be None)
print(ds.captions)  # List of strings or None values

from hypergen.dataset import Dataset
from pathlib import Path

class MyCustomDataset(Dataset):
    def __getitem__(self, idx):
        # Custom loading logic
        image, caption = super().__getitem__(idx)

        # Apply custom preprocessing
        # ...

        return image, caption

ValueError: No images found in ./my_images with extensions ['.jpg', '.jpeg', ...]

for image, caption in ds:
    if caption is None:
        print("Image has no caption")
    else:
        print(f"Caption: {caption}")

# When creating caption files, specify UTF-8
with open("photo1.txt", "w", encoding="utf-8") as f:
    f.write("Your caption with �mojis and -�")

art_style_dataset/
  painting1.jpg
  painting1.txt     <- "Abstract painting with blue and red geometric shapes"
  painting2.jpg
  painting2.txt     <- "Impressionist landscape with trees and water"
  painting3.jpg
  painting3.txt     <- "Cubist portrait with angular features"
  ...

character_dataset/
  portrait1.jpg
  portrait1.txt     <- "Close-up portrait of John facing forward"
  portrait2.jpg
  portrait2.txt     <- "John smiling in profile view"
  portrait3.jpg
  portrait3.txt     <- "Full body shot of John wearing a suit"
  ...

product_dataset/
  product1.jpg
  product1.txt      <- "Red sneaker on white background from side angle"
  product2.jpg
  product2.txt      <- "Red sneaker on white background from top view"
  product3.jpg
  product3.txt      <- "Red sneaker on white background from front"
  ...