Study
Computer Vision · Image basics
Images as arrays: height × width × channels, uint8 vs float, RGB vs grayscale, cropping, and the channel-order and range traps between libraries.
- A colour image is just an H × W × 3 array of numbers, usually uint8 from 0 to 255.
- PyTorch wants channels first (C × H × W) and floats in [0, 1]; most image libraries give channels last.