C14096073_GAI_Project4

Environment

Install the required packages:

pip install -r requirements.txt

To train the DDPM on MNIST, run:

python train_mnist.py

To execute the DIP training and the DDPM reverse process, run:

python main.py

You will obtain two images: one generated by DDPM+DIP (ddpm_dip.png) and another by DDPM alone (ddpm_nodip.png).

Name		Name	Last commit message	Last commit date
Latest commit History 13 Commits
__pycache__		__pycache__
data		data
deep-image-prior-master		deep-image-prior-master
mnist_data/MNIST/raw		mnist_data/MNIST/raw
mnist_png		mnist_png
models		models
results		results
utils		utils
.gitignore		.gitignore
Dockerfile		Dockerfile
LICENSE		LICENSE
README.md		README.md
activation_maximization.ipynb		activation_maximization.ipynb
ddpm_dip.png		ddpm_dip.png
ddpm_nodip.png		ddpm_nodip.png
denoising.ipynb		denoising.ipynb
environment.yml		environment.yml
feature_inversion.ipynb		feature_inversion.ipynb
flash-no-flash.ipynb		flash-no-flash.ipynb
inference.py		inference.py
inpainting.ipynb		inpainting.ipynb
main.py		main.py
model.py		model.py
requirements.txt		requirements.txt
resize.py		resize.py
restoration.ipynb		restoration.ipynb
sr_prior_effect.ipynb		sr_prior_effect.ipynb
super-resolution.ipynb		super-resolution.ipynb
super-resolution_eval_script.py		super-resolution_eval_script.py
train_mnist.py		train_mnist.py
unet.py		unet.py
utils2.py		utils2.py