This repository provides the official PyTorch implementation of our paper "Context-Aware Mutual Learning for Blind Image Inpainting and Beyond".
- Qualitative comparison results of unseen contaminated patterns for blind image inpainting.
- Linux
- Python 3.7
- NVIDIA GPU + CUDA CuDNN
- Clone this repo:
git clone https://github.com/zhenglab/CAML.git
cd CAML- Install PyTorch and 1.4 and other dependencies (e.g., torchvision).
- For Conda users, you can create a new Conda environment using
conda create --name <env> --file requirements.txt.
- For Conda users, you can create a new Conda environment using
python train.py --path=$configpath$
For example: python train.py --path=./checkpoints/
python test.py --path=$configpath$
For example: python test.py --path=./checkpoints/
- Download pre-trained models from BaiduCloud (access code: 7qmx), and put
g.pthe.pthd.pthdp.pthin the directorycheckpoints.