Skip to contents

If your directory structure is:

main_directory/
...class_a/
......a_image_1.jpg
......a_image_2.jpg
...class_b/
......b_image_1.jpg
......b_image_2.jpg

Then calling image_dataset_from_directory(main_directory, labels = 'inferred') will return a tf.data.Dataset that yields batches of images from the subdirectories class_a and class_b, together with labels 0 and 1 (0 corresponding to class_a and 1 corresponding to class_b).

Supported image formats: .jpeg, .jpg, .png, .bmp, .gif. Animated gifs are truncated to the first frame.

Usage

image_dataset_from_directory(
  directory,
  labels = "inferred",
  label_mode = "int",
  class_names = NULL,
  color_mode = "rgb",
  batch_size = 32L,
  image_size = list(256L, 256L),
  shuffle = TRUE,
  seed = NULL,
  validation_split = NULL,
  subset = NULL,
  interpolation = "bilinear",
  follow_links = FALSE,
  crop_to_aspect_ratio = FALSE,
  data_format = NULL
)

Arguments

directory

Directory where the data is located. If labels is "inferred", it should contain subdirectories, each containing images for a class. Otherwise, the directory structure is ignored.

labels

Either "inferred" (labels are generated from the directory structure), NULL (no labels), or a list/tuple of integer labels of the same size as the number of image files found in the directory. Labels should be sorted according to the alphanumeric order of the image file paths (obtained via os.walk(directory) in Python).

label_mode

String describing the encoding of labels. Options are:

  • "int": means that the labels are encoded as integers (e.g. for sparse_categorical_crossentropy loss).

  • "categorical" means that the labels are encoded as a categorical vector (e.g. for categorical_crossentropy loss).

  • "binary" means that the labels (there can be only 2) are encoded as float32 scalars with values 0 or 1 (e.g. for binary_crossentropy).

  • NULL (no labels).

class_names

Only valid if labels is "inferred". This is the explicit list of class names (must match names of subdirectories). Used to control the order of the classes (otherwise alphanumerical order is used).

color_mode

One of "grayscale", "rgb", "rgba". Defaults to "rgb". Whether the images will be converted to have 1, 3, or 4 channels.

batch_size

Size of the batches of data. Defaults to 32. If NULL, the data will not be batched (the dataset will yield individual samples).

image_size

Size to resize images to after they are read from disk, specified as (height, width). Defaults to (256, 256). Since the pipeline processes batches of images that must all have the same size, this must be provided.

shuffle

Whether to shuffle the data. Defaults to TRUE. If set to FALSE, sorts the data in alphanumeric order.

seed

Optional random seed for shuffling and transformations.

validation_split

Optional float between 0 and 1, fraction of data to reserve for validation.

subset

Subset of the data to return. One of "training", "validation", or "both". Only used if validation_split is set. When subset = "both", the utility returns a tuple of two datasets (the training and validation datasets respectively).

interpolation

String, the interpolation method used when resizing images. Defaults to "bilinear". Supports "bilinear", "nearest", "bicubic", "area", "lanczos3", "lanczos5", "gaussian", "mitchellcubic".

follow_links

Whether to visit subdirectories pointed to by symlinks. Defaults to FALSE.

crop_to_aspect_ratio

If TRUE, resize the images without aspect ratio distortion. When the original aspect ratio differs from the target aspect ratio, the output image will be cropped so as to return the largest possible window in the image (of size image_size) that matches the target aspect ratio. By default (crop_to_aspect_ratio = FALSE), aspect ratio may not be preserved.

data_format

If NULL uses config_image_data_format() otherwise either 'channel_last' or 'channel_first'.

Value

A tf.data.Dataset object.

  • If label_mode is NULL, it yields float32 tensors of shape (batch_size, image_size[0], image_size[1], num_channels), encoding images (see below for rules regarding num_channels).

  • Otherwise, it yields a tuple (images, labels), where images has shape (batch_size, image_size[0], image_size[1], num_channels), and labels follows the format described below.

Rules regarding labels format:

  • if label_mode is "int", the labels are an int32 tensor of shape (batch_size,).

  • if label_mode is "binary", the labels are a float32 tensor of 1s and 0s of shape (batch_size, 1).

  • if label_mode is "categorical", the labels are a float32 tensor of shape (batch_size, num_classes), representing a one-hot encoding of the class index.

Rules regarding number of channels in the yielded images:

  • if color_mode is "grayscale", there's 1 channel in the image tensors.

  • if color_mode is "rgb", there are 3 channels in the image tensors.

  • if color_mode is "rgba", there are 4 channels in the image tensors.