TinyDiffusion

Kaggle Implementation:#

Data Preparation#

git clone to download tinydiffusion locally
Download the cifar-10-python dataset to the datasets/ folder, maintaining the directory structure as datasets/cifar-10-batches-py.
Package and upload to Kaggle dataset, named cifar-10-python.

Run#

Create a new notebook, add the dataset cifar-10-python as input.
Run the default code
Configure the environment

!pip install -r /kaggle/input/tinydiffusion/TinyDiffusion/ddpm/requirements.txt

Copy the dataset to the output path

import shutil
import os

# Define the input and output directories for the dataset
input_dir = '/kaggle/input/tinydiffusion'
output_dir = '/kaggle/output/tinydiffusion'

# Check if the output directory exists, if not, create it
if not os.path.exists(output_dir):
    os.makedirs(output_dir)

# Traverse all files and folders in the input directory
for root, dirs, files in os.walk(input_dir):
    # Build the corresponding output directory
    relative_path = os.path.relpath(root, input_dir)
    output_sub_dir = os.path.join(output_dir, relative_path)
    
    # If the output subdirectory does not exist, create it
    if not os.path.exists(output_sub_dir):
        os.makedirs(output_sub_dir)
    
    # Copy files to the output directory
    for file in files:
        input_file_path = os.path.join(root, file)
        output_file_path = os.path.join(output_sub_dir, file)
        shutil.copy2(input_file_path, output_file_path)

print("Dataset copy completed!")

Create a path to store images generated every 10 epochs

import os

# Define the target directory for saving images
save_dir = '/kaggle/output/tinydiffusion/TinyDiffusion/samples'

# Check if the directory exists, if not, create it
if not os.path.exists(save_dir):
    os.makedirs(save_dir)
    print(f"Successfully created directory: {save_dir}")
else:
    print(f"Directory {save_dir} already exists.")

Enter the output path

cd /kaggle/output/tinydiffusion/TinyDiffusion

Process the data

!python /kaggle/input/tinydiffusion/TinyDiffusion/ddpm/dataloader.py

Print the structure

!python /kaggle/input/tinydiffusion/TinyDiffusion/ddpm/unet.py

Add noise to the images

!python /kaggle/input/tinydiffusion/TinyDiffusion/ddpm/diffusion.py

Train, here only training for 100 times, if you want to modify, you can change it in the command line

!python /kaggle/output/tinydiffusion/TinyDiffusion/ddpm/train.py --epochs 100 --batch_size 128 --lr 1e-4 --img_size 32

View the images

import os
from PIL import Image
import matplotlib.pyplot as plt

# Define the image directory
save_dir = '/kaggle/output/tinydiffusion/TinyDiffusion/samples'

# Check if the directory exists
if not os.path.exists(save_dir):
    print(f"Directory {save_dir} does not exist.")
else:
    # Get all files in the directory
    all_files = os.listdir(save_dir)
    
    # Filter out image files (assuming image file extensions are .png, .jpg, .jpeg)
    image_files = [f for f in all_files if f.lower().endswith(('.png', '.jpg', '.jpeg'))]
    
    if not image_files:
        print(f"There are no image files in the directory {save_dir}.")
    else:
        print(f"Found the following image files:")
        for idx, image_file in enumerate(image_files):
            print(f"{idx + 1}. {image_file}")
            # Display the image (optional)
            image_path = os.path.join(save_dir, image_file)
            img = Image.open(image_path)
            plt.imshow(img)
            plt.title(image_file)
            plt.axis('off')
            plt.show()

Hanah

TinyDiffusion

Kaggle Implementation:#

Data Preparation#

Run#

Results#