Dimensions are the axes, coordinates, or components used to describe tensors, vectors, matrices, feature vectors, or embedding spaces. The term may refer to tensor rank, the number of entries in a feature vector, or the size of an embedding representation.
Overloaded term having any of the following definitions: - The number of levels of coordinates in a Tensor. For example: - A scalar has zero dimensions; for example, . - A vector has one dimension; for example, . - A matrix has two dimensions; for example, . You can uniquely specify a particular cell in a one-dimensional vector with one coordinate; you need two coordinates to uniquely specify a particular cell in a two-dimensional matrix. - The number of entries in a feature vector. - The number of elements in an embedding layer.