NHWC is an acronym describing the order of the axes in a tensor containing image data samples.

Software frameworks for training machine learning models–such as TensorFlow–use the acronym NHWC

• N: Number of data samples.
• H: Image height.
• W: Image width.
• C: Image channels. A red-green-blue (RGB) image will have 3 channels.

NHWC is sometimes referred to as a channels-last layout.