A tensor is an N-dimensional data structure used to represent numerical or symbolic values in machine learning frameworks. Scalars, vectors, and matrices are lower-dimensional forms of tensors, while higher-rank tensors can represent more complex data such as images, batches, and sequences.
The primary data structure in TensorFlow programs. Tensors are N-dimensional (where N could be very large) data structures, most commonly scalars, vectors, or matrixes. The elements of a Tensor can hold integer, floating-point, or string values.