Yili Wang, Xin Li, Kun Xu, Dongliang He, Qi Zhang, Fu Li, Errui Ding
-
Clone this repo
git clone https://github.com/amberwangyili/neurop-pytorch
-
Download the Dataset from 百度网盘 (code:jvvq) and unzip in project folder
tree -L 2 neurop-pytorch/datasets # the output should be like the following: datasets/ ├── dataset-dark │ ├── testA │ ├── testB │ ├── trainA │ └── trainB ├── dataset-init │ ├── BC │ ├── EX │ └── VB ├── dataset-lite │ ├── testA │ ├── testB │ ├── trainA │ └── trainB └── dataset-ppr ├── ppr-a ├── ppr-b ├── ppr-c ├── testA ├── testM ├── trainA └── trainM
-
Install Dependencies
cd neurop-pytorch/codes pip install -r requirements.txt
-
We provide pretrained model weights for MIT-Adobe FiveK and PPR10K in
neurop-pytorch/pretrain_models/
-
Run command:
python test.py -config configs/test/<configuaration-name>.yaml
-
The evaluation results will be in the
neurop-pytorch/results
folder
-
Initialization individual neural color operators:
python train.py -config ./configs/init_neurop.yaml
-
Finetune with strength predictors:
python train.py -config ./configs/train/<configuration-name>.yaml