Set14HR#
- class deepinv.datasets.Set14HR(root: str, download: bool = False, transform: Callable | None = None)[source]#
Bases:
Dataset
Dataset for Set14.
The Set14 dataset 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 --- image_SRF_2 --- img_001_SRF_2_bicubic.png | | | | | -- img_014_SRF_2_SRCNN.png | | | -- image_SRF_3 --- ... | -- image_SRF_4 --- ... | -- Set14_SR.zip
This dataset wrapper gives access to the 14 high resolution images in the image_SRF_4 folder. Raw dataset source : jbhuang0604/SelfExSR
- 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:
Instanciate 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
- check_dataset_exists() bool [source]#
Verify that the image folders exist and contain all the images.
self.root should have the following structure:
self.root --- Set14 --- image_SRF_2 --- img_001_SRF_2_bicubic.png | | | | | -- img_014_SRF_2_SRCNN.png | | | -- image_SRF_3 --- ... | -- image_SRF_4 --- ... | -- xxx -- xxx