You can find here a list of common image super resolution datasets on huggingface datasets
for use with the super-image
library.
dataset | train | validation | test |
---|---|---|---|
Div2k | 800 | 100 | - |
Set5 | - | 5 | - |
Set14 | - | 14 | - |
BSD100 | - | 100 | - |
Urban100 | - | 100 | - |
PIRM | - | 100 | 100 |
Quickly evaluate models on super image resolution datasets.
Install with pip
:
pip install datasets super-image
Evaluate a model with the super-image
library:
from datasets import load_dataset
from super_image import EdsrModel
from super_image.data import EvalDataset, EvalMetrics
dataset = load_dataset('eugenesiow/Set5', 'bicubic_x2', split='validation')
eval_dataset = EvalDataset(dataset)
model = EdsrModel.from_pretrained('eugenesiow/edsr-base', scale=2)
EvalMetrics().evaluate(model, eval_dataset)