Skip to content

Video Super Resolution library that implements training and evaluation of video super resolution architectures. Metrics and SoA architectures are already implemented, for quick fine-tuning and evaluation.

Notifications You must be signed in to change notification settings

santurini/vsrlab

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Video Super Resolution Playground

A library to train, test and develop Video Super Resolution architectures. The framework is based on Hydra and offers a variety of SoA architectures (Real Basic VSR, VRT) already implemented and ready to be trained.

Create venv

conda create -n vsrlab python=3.11
conda activate vsrlab

pip3 install -r requirements.txt
Install the package locally
git clone https://github.com/santurini/vsrlab.git

cd vsrlab && pip3 install .

Quick examples

python train.py +experiment=basic
# to resume a training -> change 'restore' and 'restore_opt' fields in experiment config file 

python test.py +experiment=test cfg_dir=path/to/checkpoints_dir/experiment_name
# checkpoints directory should contain 'checkpoint/last.ckpt' and 'config.yaml'

About

Video Super Resolution library that implements training and evaluation of video super resolution architectures. Metrics and SoA architectures are already implemented, for quick fine-tuning and evaluation.

Topics

Resources

Stars

Watchers

Forks

Languages