Conv3d Output Size Calculator
Calculate PyTorch Conv3d output depth, height, and width. Enter input shape, kernel size, stride, padding, and dilation for 3D convolution output dimensions.
Built by Michael Lip
Frequently Asked Questions
What is the Conv3d output size formula?
The formula is the same as Conv2d but applied to 3 spatial dimensions: D_out = floor((D_in + 2*padding - dilation*(kernel_size-1) - 1) / stride) + 1. The same formula applies independently to height and width.
When should I use Conv3d instead of Conv2d?
Use Conv3d for volumetric data: 3D medical images (MRI, CT scans), video frames (time × height × width), and point cloud voxelizations. The input shape is (batch, channels, depth, height, width), 5 dimensions total.
How many parameters does Conv3d have?
Conv3d parameters = out_channels × (in_channels × kernel_d × kernel_h × kernel_w + 1 if bias). A Conv3d(3, 64, kernel_size=3) has 64 × (3 × 3 × 3 × 3 + 1) = 5,248 parameters. This is 3× more per kernel element than Conv2d.
Why is Conv3d so memory-intensive?
Conv3d processes 3 spatial dimensions, so the output tensor has 5 dimensions. A single feature map at 64×64×64 uses 262K floats vs 4K for a 64×64 Conv2d map. Memory scales cubically with spatial resolution.
Is this tool free?
Yes. All HeyTensor tools are free, run in your browser, and require no signup.
About This Tool
Part of HeyTensor. All calculations run in your browser. Source code on GitHub.
Contact
Built by Michael Lip. Email [email protected].
TENSOR PREFLIGHT · DOWNLOADABLE PYTORCH TOOLKIT
Take the next step in your own PyTorch model.
Trace a local forward pass, inspect tensor shapes in an HTML report, and turn a repair into a regression check. Includes eight broken-and-fixed workflows, source code and setup instructions.
Is this toolkit right for my problem?
Use the free calculator for a layer formula or a quick shape check.
Consider Tensor Preflight when you have a local PyTorch model and want a forward-pass report plus repeatable checks. Python 3.9+ and PyTorch 2.8+ are required. It does not run your model in this website or automatically repair it.
Open the sample report before buying to check the output format.
Python 3.9+ · PyTorch 2.8+ · Runs locally