Follow the steps below to set up the project environment and run the necessary files.
Create a new Conda environment with Python 3.10.12 using the conda-forge channel:
conda create --name py310 python=3.10.12 -c conda-forge
Activate the newly created environment:
conda activate py310
Install the required packages from the `requirements.txt` file:
pip install -r requirements.txt
Run the script to download and extract the necessary files:
python extract_files.py
If the script doesn't work, follow these manual steps:
- Go to this Google Drive link.
- Download the zip file.
- Place the zip file in the root directory of this repository.
- Extract the contents into a folder called `Restormer` in the root directory.
Go to pytorch.org to get the appropriate installation command for your system based on the CUDA version and your preference. Here are some common options:
pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118
pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121
conda install pytorch torchvision torchaudio pytorch-cuda=11.8 -c pytorch -c nvidia
conda install pytorch torchvision torchaudio pytorch-cuda=12.1 -c pytorch -c nvidia
Finally, run the main script:
python main.py