TensorFlow, which was released to the public in November 2015. It quickly turned into a popular library for machine learning, and it is currently being used for natural language processing, artificial intelligence, computer vision, and predictive analytics.
A suite of software While “TensorFlow” is primarily used to refer to the API used to build and train machine learning models, TensorFlow is really a bundle of software designed to be used in tandem with:
TensorFlow is the API for defining machine learning models, training them with data, and exporting them for further use.
TensorBoard is graph visualization software that is included with any standard TensorFlow installation.
TensorFlow Serving is software that facilitates easy deployment of pre-trained TensorFlow models.
So what is a Tensor
A tensor is a multidimensional array of numbers. In fact, vectors and matrices can be treated as 1-D and 2-D tensors. In deep learning, tensors are mostly used for storing and processing data. For example, an image in RGB is stored in a three-dimensional tensor, where along one dimension we have the horizontal axis and along the other dimension we have the vertical axis, and where the third dimension corresponds to the three color channels, namely Red, Green, and Blue. Another example is the four-dimensional tensors used in feeding images through mini-batches in a convolutional neural network. Along the first dimension we have the image number in the batch and along the second dimension we have the color channels, and the third and fourth dimensions correspond to pixel location in the horizontal and vertical directions.