Convolution Layer Output Shape Calculator
Calculate square 2D convolution output dimensions, grouped parameter count and multiply-accumulate count.
YOUR CALCULATION
Result
—
Calculation steps
Work through one step at a time or reveal the complete calculation. The steps use your current inputs.
How to calculate
Use symmetric zero padding, square spatial inputs and grouped connections with one bias per output channel.
Output=floor((input+2padding−dilation(kernel−1)−1)/stride+1); weights=Cout(Cin/groups)kernel²
Worked example
224 input, kernel 3, stride 2, padding 1 and dilation 1 produce 112×112 output.
Assumptions and input details
Both channel counts must divide by groups. No framework execution, tensor storage, activation, normalization, batch dimension or hardware timing is included. MAC counts omit bias additions.
References: PyTorch: Conv2d shape
Using this calculator
Can I enter my own problem?
Yes. Replace the example values with your own inputs. The result, calculation steps, tables and applicable diagrams update from those inputs. Blank or invalid values clear the result; example values are never silently substituted for missing inputs.
Are the results exact?
Results use floating-point arithmetic and displayed rounding. Read the formula, assumptions and any stated data precision before interpreting the result.
Is my input uploaded?
The calculation runs in your browser. No account, file upload or external AI service is required. Inputs are not saved between page reloads.
Calculate full linear or zero-padded circular convolution of two numeric sequences, with every output index shown.
Calculate an ideal compute-or-memory throughput roof from entered operations, bytes moved and hardware ceilings.
Estimate a replacement drive’s rebuild time and I/O volume from capacity, copied fraction, aggregate throughput and foreground reserve.
Reserved advertising space.