- To install all dependencies, run
pip install pytorch && pip install Pillow && pip install torchvision
- To download the dataset, run the
DownloadData.py
file. This will download the MIT Places Dataset using torchvision's dataset loader. - To create masked images, run the
MakeData.py
file. This will preprocess the images by adding a mask at the center of the screen. - To run the baseline analytical inpainting solutions, follow the instructions on the
AnalyticalSolns.ipynb
file. - To run the GAN inpainting solution, follow the instructions on the
inpaint.ipynb
file.
-
Notifications
You must be signed in to change notification settings - Fork 0
kev-kim/Image-Infilling-GAN
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
Image inpainting with a generative adversarial network.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published
Languages
- Jupyter Notebook 100.0%