Common data tensors in real-world example

  1. Vector data – Rank-2 shape tensor such as sample, features where each sample is a vector of numerical attributes.
  2. Timeseries data or sequence data – Rank-3 tensor with the shape (samples, timesteps, features) where each sample is a sequence of timesteps of feature vectors.
  3. Images – Rank-4 tensors with shape (samples, height, width, channels) where each sample is 2D grid of pixels. Each pixel is represented by a vector of values (channels).
  4. Video – Rank-5 tensors with shape (samples, frames, height, width, channels) where each sample is a sequence of images.

Categories:

Tags:

No responses yet

Leave a Reply

Your email address will not be published. Required fields are marked *

Cookie Consent with Real Cookie Banner