Datasests

CsvImageFolder

class sconce.datasets.CsvImageFolder(root, csv_path, filename_key='image_name', labels_key='tags', csv_delimiter=',', labels_delimiter=' ', loader=<function default_loader>, extensions=['.jpg', '.jpeg', '.png', '.ppm', '.bmp', '.pgm', '.tif'], transform=None, target_transform=None)[source]

A Dataset that reads images from a folder and labels from a csv file.

Parameters:
  • root (string) – directory where the images can be found.
  • csv_path (string) – the path to the csv file containing image filenames and labels.
  • filename_key (string, optional) – the column header of the csv for the column that contains image filenames (without extensions).
  • labels_key (string, optional) – the column header of the csv for the column that contains labels for each image.
  • csv_delimiter (string, optional) – the character(s) used to separate fields in the csv file.
  • loader (callable, optional) – a function to load a sample given its path.
  • extensions (list[string], optinoal) – a list of allowed extensions. E.g, ['.jpg', '.tif']
  • transform (callable, optional) – A function/transform that takes in a sample and returns a transformed version. E.g, transforms.RandomCrop for images.
  • target_transform (callable, optional) – A function/transform that takes in the target and transforms it.