tf.squeeze

Removes dimensions of size 1 from the shape of a tensor. ... this op does not accept a deprecated squeeze_dims argument.

tf.data.Dataset

All input tensors must have the same size in their first dimensions.

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.

tf.reshape

To instead reorder the data to rearrange the dimensions of a tensor, see tf.transpose . t = [[1, 2, 3], [4, 5, 6]] tf.reshape(t, [3, ...

tf.sparse.SparseTensor

Takes a list indicating the number of elements in each dimension. For example, dense_shape=[3,6] specifies a two-dimensional 3x6 tensor, ...

tf.RaggedTensor

Please use one of the following methods to construct a RaggedTensor :.

tf.Tensor

In some cases, the inferred shape may have unknown dimensions.

tf.gather

from params axis axis according to indices . indices must be an integer tensor of any dimension (often 1-D).

tf.boolean_mask

In general, 0 < dim(mask) = K <= dim(tensor) , and mask 's shape must match the first K dimensions of tensor 's shape.

tf.Variable

In other words, the dimensions should be the following:.