Neural Network Parameter Calculator

Build layered architectures, estimate trainable parameters, output shapes, memory, optimiser states, LoRA additions, and export clear neural network summaries for efficient planning and comparison.

Calculation results

Architecture flow

Layer-by-layer summary

# Layer Type Input Output Weights Biases Trainable Non-trainable Total Share Memory

Parameter distribution

Memory estimate

Model configuration

Set the model-wide assumptions used for parameter and memory calculations.

Estimated activations = parameter memory × multiplier × batch size.
%

Architecture builder

Add, duplicate, remove, reorder, freeze, or disable layers.

LoRA and adapter estimation

Estimate extra trainable parameters for low-rank adaptation modules.

Formula used

Dense: (input features × output units) + output biases
Convolution: ((input channels ÷ groups) × kernel elements × filters) + filter biases
Depthwise convolution: input channels × depth multiplier × kernel elements + biases
Separable convolution: depthwise parameters + pointwise parameters
Embedding: vocabulary size × embedding dimension
Simple RNN: hidden × (input + hidden + bias terms)
GRU: 3 × hidden × (input + hidden + bias terms)
LSTM: 4 × hidden × (input + hidden + bias terms)
Attention: Q, K, V projections + output projection
LoRA: rank × (input dimension + output dimension) × adapted modules
Convolution output: floor((N + 2P - D(K - 1) - 1) ÷ S + 1)

How to use

Set model-wide precision and memory assumptions first. Choose an optimiser and batch size. Add activation estimates only when needed.

Add each neural network layer in order. Enter dimensions, kernels, heads, or hidden sizes. Freeze layers when their weights will not train.

Press Calculate parameters to build the report. Review layer shares and memory estimates. Export the result using one available format.

Example data

LayerConfigurationParameters
Input784 features0
Dense 1784 × 128 + 128100,480
Dense 2128 × 64 + 648,256
Output64 × 10 + 10650
Total109,386

Frequently asked questions

What is a trainable parameter?

A trainable parameter is updated during optimisation. Weights and enabled biases are common examples. Frozen values remain unchanged during training.

Why do convolution layers use fewer parameters?

Convolution layers reuse kernels across spatial positions. Weight sharing reduces parameter growth. Large feature maps can still require substantial activation memory.

Are batch-normalisation statistics trainable?

Scale and offset values are usually trainable. Moving mean and variance are usually non-trainable. Framework implementations may differ slightly.

Does batch size change parameter count?

Batch size does not change learned parameters. It changes activation memory and throughput. Larger batches can require much more training memory.

How is Adam memory estimated?

Adam commonly stores two optimiser-state tensors. Gradients require another parameter-sized tensor. Mixed precision may add master weights.

What does pruning percentage mean?

Pruning removes or masks selected weights. Sparse storage may reduce effective memory. Actual speed gains depend on hardware and libraries.

How are bidirectional recurrent layers counted?

Bidirectional layers maintain two recurrent directions. Their parameters are approximately doubled. Output features also commonly double.

Are preset results exact?

Presets demonstrate common layer patterns. Named architectures vary across implementations. Confirm exact settings against your framework model summary.

Are parameters the same as FLOPs?

Parameters measure stored learned values. FLOPs estimate computation for a forward or training pass. Neither metric alone describes total performance.

Related Calculators

Activation Function CalculatorReLU Function CalculatorTanh Function CalculatorNeural Network Weighted Sum CalculatorForward Propagation CalculatorBackpropagation Gradient CalculatorLearning Rate CalculatorEpoch and Iteration CalculatorDropout CalculatorWeight Initialization Calculator

Important Note: All the Calculators listed in this site are for educational purpose only and we do not guarentee the accuracy of results. Please do consult with other sources as well.