tf.data.Dataset from image files in a directory.
tf.keras.preprocessing.image_dataset_from_directory( directory, labels='inferred', label_mode='int', class_names=None, color_mode='rgb', batch_size=32, image_size=(256, 256), shuffle=True, seed=None, validation_split=None, subset=None, interpolation='bilinear', follow_links=False )
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
image_dataset_from_directory(main_directory, labels='inferred') will return a
tf.data.Dataset that yields batches of images from the subdirectories
class_b, together with labels 0 and 1 (0 corresponding to
class_a and 1 corresponding to
Supported image formats: jpeg, png, bmp, gif. Animated gifs are truncated to the first frame.
| || Directory where the data is located. If |
| || Either "inferred" (labels are generated from the directory structure), 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 |
| || |
| ||Only valid if "labels" is "inferred". This is the explict list of class names (must match names of subdirectories). Used to control the order of the classes (otherwise alphanumerical order is used).|
| ||One of "grayscale", "rgb", "rgba". Default: "rgb". Whether the images will be converted to have 1, 3, or 4 channels.|
| ||Size of the batches of data. Default: 32.|
| || Size to resize images to after they are read from disk. Defaults to |
| ||Whether to shuffle the data. Default: True. If set to False, sorts the data in alphanumeric order.|
| ||Optional random seed for shuffling and transformations.|
| ||Optional float between 0 and 1, fraction of data to reserve for validation.|
| || One of "training" or "validation". Only used if |
| || String, the interpolation method used when resizing images. Defaults to |
| ||Whether to visits subdirectories pointed to by symlinks. Defaults to False.|
| A |
Rules regarding labels format:
int, the labels are an
int32tensor of shape
binary, the labels are a
float32tensor of 1s and 0s of shape
categorial, the labels are a
float32tensor of shape
(batch_size, num_classes), representing a one-hot encoding of the class index.
Rules regarding number of channels in the yielded images:
grayscale, there's 1 channel in the image tensors.
rgb, there are 3 channel in the image tensors.
rgba, there are 4 channel in the image tensors.
© 2020 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 3.0.
Code samples licensed under the Apache 2.0 License.