computer-vision
Image tensors -- batch and channel conventions for vision models
taught
Reading a vision model's tensor shape -- an added batch axis (how many images at once) stacked with an image's existing height/width/channel axes -- and the channels-first vs. channels-last layout choice, as a library convention rather than a mathematical rule.
Taught in
-
Images as tensors: shape, channels, and batches
Computer Vision
Requires
-
matrices-notation-shape-and-special-forms
required
The batch dimension is one more index tacked onto the same scalar/vector/matrix/tensor shape vocabulary linear-algebra already built.
Required by
Nothing in the catalog needs this yet.
Local knowledge map
Local knowledge map
Click to expand
Solid arrows are required prerequisites; dashed are recommended or helpful. Lower rows are more foundational. Click any box to jump to that concept.