keras.utils.text_dataset_from_directory( directory, labels="inferred", label_mode="int", class_names=None, batch_size=32, max_length=None, shuffle=True, seed=None, validation_split=None, subset=None, follow_links=False, )
tf.data.Dataset from text files in a directory.
If your directory structure is:
main_directory/ ...class_a/ ......a_text_1.txt ......a_text_2.txt ...class_b/ ......b_text_1.txt ......b_text_2.txt
labels='inferred') will return a
tf.data.Dataset that yields batches of
texts from the subdirectories
class_b, together with labels
0 and 1 (0 corresponding to
class_a and 1 corresponding to
.txt files are supported at this time.
"inferred", it should contain subdirectories, each containing text files for a class. Otherwise, the directory structure is ignored.
"inferred"(labels are generated from the directory structure),
None(no labels), or a list/tuple of integer labels of the same size as the number of text files found in the directory. Labels should be sorted according to the alphanumeric order of the text file paths (obtained via
labels. Options are: -
"int": means that the labels are encoded as integers (e.g. for
"categorical"means that the labels are encoded as a categorical vector (e.g. for
"binary"means that the labels (there can be only 2) are encoded as
float32scalars with values 0 or 1 (e.g. for
"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).
None, the data will not be batched (the dataset will yield individual samples).
True. If set to
False, sorts the data in alphanumeric order.
"both". Only used if
validation_splitis set. When
subset="both", the utility returns a tuple of two datasets (the training and validation datasets respectively).
None, it yields
stringtensors of shape
(batch_size,), containing the contents of a batch of text files.
(texts, labels), where
labelsfollows the format described below.
Rules regarding labels format:
int, the labels are an
int32tensor of shape
binary, the labels are a
float32tensor of 1s and 0s of shape
categorical, the labels are a
float32tensor of shape
(batch_size, num_classes), representing a one-hot encoding of the class index.