Computer Vision
Pixels, filters, feature maps and the convolutional stack that turns an image into a prediction.
About this track
A convolutional network is usually drawn as a row of coloured boxes that explains nothing. This track takes the boxes apart: what a filter is, what it produces, why the output shrinks, what padding restores, and what a stride costs you.
It starts with how an image is stored at all - grayscale intensities, then RGB channels - and finishes on the practical layer: augmentation, data loaders and transfer learning.
The stack is taken apart rather than drawn as coloured boxes: what a filter contains, what a feature map records, what pooling discards, and how many parameters each of those choices actually costs.
What you will be able to do
- Explain what a convolutional filter is and why it spans every input channel.
- Compute a layer's output size from the input, kernel, padding and stride.
- Count a convolutional layer's parameters, and say why the image size never appears.
- Describe what pooling buys and what it destroys.
- Say why weight sharing gives both a parameter saving and translation equivariance.
How the track is ordered
It starts below the network, with how an image is stored at all - grayscale intensities, then RGB channels - because a filter's depth only makes sense once channels do. Then the convolution itself: edge detection by hand, feature maps, padding, stride, pooling and parameter counting. After that the components that make a real network work, including ReLU, dense layers and residual connections, and finally the applied layer: augmentation, data loaders, transfer learning, object detection and segmentation. The deep learning track is assumed.
Where this leads
Transfer learning is where most practical vision work actually starts, and the generative AI track covers the modern architectures that now compete with convolutional networks on the same tasks.
All 47 modules, in teaching order
- 01How Neural Networks Process ImagesLearn how Neural Networks process images by flattening 2D pixels into 1D arrays with this interactive visualization on VizLearn.
- 02Grayscale Image ProcessingSee a grayscale image for what it is: a grid of brightness numbers you can filter, threshold and edit directly.
- 03RGB Image ProcessingSplit a colour image into red, green and blue channels and see how three grids of numbers combine into every pixel.
- 04Colour Spaces: RGB and HSV
- 05Histograms and Equalisation
- 06Thresholding
- 07Erosion and Dilation
- 08Blur: Gaussian, Median and Bilateral
- 09Convolution Kernels by Hand
- 10Real-time Edge DetectionSlide a sensitivity threshold across a real image and watch edges appear wherever brightness changes sharply enough.
- 11Resizing and Interpolation
- 12Affine Transforms
- 13Template Matching
- 14Harris Corners and Keypoints
- 15Haar Cascade Detection ModelsDrag a Haar rectangle feature over a face, watch the integral image sum it in four lookups, and see a cascade discard 24,000 windows.
- 16Convolutional LayerDrag a convolution filter across an image and watch it build a feature map one value at a time, the core operation inside a CNN.
- 17Receptive Field
- 18Padding in CNNLearn how Padding works in Convolutional Neural Networks with an interactive visualizer showing 'Valid' vs 'Same' padding on VizLearn.
- 19Strides in CNNLearn how Strides work in Convolutional Neural Networks with an interactive visualizer showing how step size downsamples feature maps on VizLearn.
- 20Parameter Sharing in CNNLearn what Parameter Sharing is in Convolutional Neural Networks and why it makes deep learning efficient on VizLearn.
- 21ReLU Activation in CNNLearn how the ReLU (Rectified Linear Unit) activation function works in Convolutional Neural Networks with this interactive visualizer on VizLearn.
- 22Pooling LayerShrink a feature map with max, average or min pooling and see how downsampling keeps the signal but discards the detail.
- 23Fully Connected Layer in CNNLearn how Fully Connected (Dense) Layers work in Convolutional Neural Networks with an interactive visualizer on VizLearn.
- 241x1 Convolutions
- 25Depthwise Separable Convolution
- 26Dilated Convolutions
- 27Global Average Pooling against Flatten
- 28Calculating Parameters in CNNLearn how to calculate the number of parameters in Convolutional Neural Networks with this interactive visualizer on VizLearn.
- 29CNN ArchitectureExplore a convolutional neural network layer by layer in 3D - see how filters, feature maps and pooling turn pixels into predictions.
- 30Data Loaders in CNNLearn how Data Loaders work in Convolutional Neural Networks, why we use batches, and how shuffling and augmentation impact training.
- 31Image Data AugmentationFlip, rotate, zoom and add noise to an image, and see how augmentation multiplies a small training set into a larger one.
- 32Transfer Learning with CNNLearn how Transfer Learning works in Convolutional Neural Networks, select models, and selectively unfreeze layers for fine-tuning.
- 33VGG-16Walk VGG-16 layer by layer and see why 89% of its 138 M parameters sit in three dense layers that do 1% of the work.
- 34InceptionNetRun the four inception branches in parallel, then switch off the 1x1 bottleneck and watch one module jump from 128 M to 303 M MACs.
- 35Anchor Boxes
- 36IoU and Non-Max SuppressionA detector proposes four boxes for two objects. IoU measures the overlap, and Non-Max Suppression uses that number to throw the duplicates away.
- 37Mean Average Precision
- 38Object Detection with Bounding BoxesDrag a predicted box toward the ground truth and watch IoU climb, the loss fall, and the detection flip from a miss to a match at the 0.5 threshold.
- 39YOLO v8See all 8,400 raw YOLO predictions, then move the confidence and NMS thresholds and watch objects appear, duplicate and disappear.
- 40ResNet and Identity ShortcutsPush a signal vector through the same contractive layer twenty times, with and without an identity shortcut, and watch one collapse toward zero while the other never can.
- 41ResNetBuild ResNet-18 through -152 from one description and watch 25.56 M parameters and 4.1 GMACs fall out of the block counts.
- 42Semantic, Instance and Panoptic Segmentation
- 43Semantic Segmentation and U-NetDownsample a mask to see more context, then upsample it back, and watch the boundary blur unless a skip connection carries the resolution pooling just destroyed.
- 44U-NetWalk U-Net level by level: 572 in, 388 out, every skip crop computed, and the case for skip connections made by turning them off.
- 45Mask R-CNNDrag a proposal on a feature map and watch RoIPool's double rounding move it eight input pixels while RoIAlign samples it exactly.
- 46Vision Transformer Patches
- 47Grad-CAM