Home▸AI & Machine Learning▸CNN Receptive Field Growth Across Layers (2D)

CNN Receptive Field Growth Across Layers (2D)

Interactive 2D CNN receptive-field visualizer: nested contour rectangles on a single input grid show exactly how far a stack of convolutional layers reaches back into the image, as you change kernel size, stride and dilation, with live feature-map size readouts.

AI & Machine Learning2DModerate60 FPS📱 Mobile-adapted⇄ 3D version

A convolutional neural network never looks at the whole image at once inside a single layer — each output unit only "sees" a small, growing patch of the input, called its receptive field. This 2D companion visualizer draws every stacked layer's receptive-field boundary as a nested contour directly on the original 32×32 input grid, alongside a shrinking-square strip of the true forward feature-map sizes, so growth-backward and shrinkage-forward are visible in the same frame. Adjust the number of layers, kernel size, stride and dilation and watch the nested boundaries expand or contract live, with the effective receptive-field size, output feature-map resolution and cumulative stride ("jump") read out numerically.

⚙ Under the hood

A 2D companion visualizer: nested contour rectangles drawn directly on a single 32x32 input grid show exactly how far a stack of convolutional layers' receptive field reaches backward into the image, alongside a shrinking-square strip of the true forward feature-map sizes, as you change kernel size, stride and dilation.

cnndeep-learningreceptive-fieldconvolutioncomputer-vision

2D · HTML5 Canvas 2D · 60 FPS target · runs fully client-side, no install