Do I need to install anything?

No. It runs in any modern browser, free, with no account required.

For Engineers · Maze Generator

Maze Generator for a convolutional net

Built for engineers using it for real design work. Go from concept to a running model in the browser, then scale to the cloud when needed. Simulate a convolutional net live below — adjust the inputs and watch it respond, right in your browser.

Maze Generator & SolverLive

recursive backtracker · BFS solve

Controls

Presets

Grid size

Show solution path

A perfect maze (exactly one path between any two cells) carved by depth-first backtracking, then solved top-left to bottom-right with breadth-first search.

▶ Run in Python

Data Inspector

Cells25²

AlgorithmDFS carve

SolverBFS shortest

Governing equation

perfect maze = spanning tree : E = N^{2} - 1 = 2 5^{2} - 1 = 624 passages

Reading this result: A perfect maze has exactly one path between any two cells, so BFS from corner to corner always finds it — here across 625 cells.

Runs locally in your browser — free forever. Scale to the cloud when reality gets heavy.

or unlock everything with Pro →

Also for:Students Researchers Educators Hobbyists & Makers K-12 Students First Responders General version →

More with Maze Generator

Maze Generator for a neural network Maze Generator for a sorting algorithm Maze Generator for a search tree Maze Generator for a hash table Maze Generator for a recommendation engine Maze Generator for an image classifier Maze Generator for a chatbot Maze Generator for a pathfinding AI

Frequently asked questions

Is this good for engineers?: Yes — this version of "Maze Generator for a convolutional net" is framed for engineers using it for real design work. Go from concept to a running model in the browser, then scale to the cloud when needed.
Do I need to install anything?: No. It runs in any modern browser, free, with no account required.