Set14HR#
- class deepinv.datasets.Set14HR(root, download=False, transform=None)[source]#
Bases:
ImageFolder
Dataset for Set14.
The Set14 dataset [1] is a dataset consisting of 14 images commonly used for testing performance of image reconstruction algorithms. Images have sizes ranging from 276×276 to 512×768 pixels.
Raw data file structure:
self.root --- Set14_HR.tar.gz | --- Set14_HR --- baboon.png | | | --- butterfly.png | --- face.png | --- ... | --- xxx
This dataset wrapper gives access to the 14 high resolution images in the
Set14_HR
folder. Raw dataset source : https://huggingface.co/datasets/eugenesiow/Set14- Parameters:
root (str) – Root directory of dataset. Directory path from where we load and save the dataset.
download (bool) – If
True
, downloads the dataset from the internet and puts it in root directory. If dataset is already downloaded, it is not downloaded again. Default at False.transform: (Callable) – (optional) A function/transform that takes in a PIL image and returns a transformed version. E.g,
torchvision.transforms.RandomCrop
- Examples:
Instantiate dataset and download raw data from the Internet
import shutil from deepinv.datasets import Set14HR dataset = Set14HR(root="Set14", download=True) # download raw data at root and load dataset Dataset has been successfully downloaded. print(dataset.check_dataset_exists()) # check that raw data has been downloaded correctly True print(len(dataset)) # check that we have 14 images 14 shutil.rmtree("Set14") # remove raw data from disk
- References: