Skip to course content
Free computer vision course

Computer Vision and Multimodal AI

Module 01 Summary

What this module established

An image is a (height, width, channels) array of numbers, and nothing in it knows what it depicts. Rows come before columns in numpy while almost every drawing API takes x before y - which is where most transposed-image bugs begin.

Carry forward

Before moving on

Move on when your dataset card exists with prohibitions and gaps, and you can state the channel order your loader produces.