tf.slice

The slice size is represented as a tensor shape, where size[i] is the number of elements of the 'i'th dimension of input_ that you want to slice. The starting ...

tf.gather

Indices are always validated on CPU and never validated on GPU. Gather slices from params axis axis according to indices . indices must be an integer tensor of ...

tf.keras.preprocessing.image.ImageDataGenerator

The function should take one argument: one image (Numpy tensor with rank 3), ...

tf.keras.utils.image_dataset_from_directory

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 ...

tf.keras.preprocessing.image.DirectoryIterator

subset, Subset of data ( "training" or "validation" ) if validation_split is set in ...

tf.where

Return the indices of non-zero elements - When only condition is provided the result is an int64 tensor where each row is the index of a non-zero element of ...

tf.data.Dataset

used for adding 1 to each element, or projecting a subset of element components.

tf.data.experimental.sample_from_datasets

(Optional.) A list or Tensor of len(datasets) floating-point values where weights[i] represents the probability to sample from datasets ...

tf.math.reduce_sum

Computes the sum of elements across dimensions of a tensor.

tf.image - Module

Resizing. The resizing Ops accept input images as tensors of several types. They always output resized images as float32 tensors. The convenience function ...