Skip to content
ENExplore Calculators

Parameter Count Calculator

Calculate the total number of parameters in a neural network architecture.

About Parameter Count Calculator

Parameter count varies by layer type. A dense (fully connected) layer has params = input × output + output, where the extra output term is the bias vector. A Conv2D layer has params = kernel_h × kernel_w × in_channels × out_channels + out_channels, since the same kernel is shared across all spatial positions. An LSTM layer has four gates (input, forget, output, cell), each acting like a dense layer over the concatenated input and hidden state, giving params = 4 × [hidden × (input + hidden)] + 4 × hidden.

Formulas

Dense layer

params = input_size * output_size + output_size

input_size
Number of input features
output_size
Number of output units (neurons)

Conv2D layer

params = kernel_h * kernel_w * in_channels * out_channels + out_channels

kernel_h
Kernel height
kernel_w
Kernel width
in_channels
Input channels
out_channels
Output channels (filters)

LSTM layer

params = 4 * (hidden * (input + hidden)) + 4 * hidden

input
Input dimension
hidden
Hidden state dimension

Worked example

With the default values below, Parameter Count Calculator returns Total Parameters of 131,328. Change any input above and every figure here is recalculated in your browser.

Inputs used

Layer Typeone of Dense (Fully Connected), Conv2D, LSTM
Dense (Fully Connected)
Input Sizeaccepts 1–1,000,000
512
Output Sizeaccepts 1–1,000,000
256
Kernel Sizeaccepts 1–64
3

Results

Total Parameters
131,328
Weight Parameters
131,072
Bias Parameters
256

Step by step

  1. 1Dense: (input × output) + output (bias)= 131,328
  2. 2Weight parameters vs. bias parameters= 131,328

Assumptions and limits

  • The result is derived only from the 4 inputs listed above. Anything not among them is not part of the calculation.
  • In particular, this calculator does not take inflation, tax, fees or charges or compounding frequency into account.
  • Figures are rounded for display to whole numbers, so totals built from several rounded parts can differ slightly from the unrounded arithmetic.

How these calculators are built and tested is described on the Methodology page. If a figure looks wrong, please report it.

Frequently Asked Questions

Why does Conv2D have far fewer parameters than Dense for the same input/output size?

Convolutional layers share the same small kernel across every spatial location, so the parameter count depends only on kernel size and channel counts, not on the spatial dimensions of the input.

Why does LSTM have 4x more parameters than a similarly-sized dense layer?

An LSTM cell contains four internal gates (input, forget, output, and cell/candidate), each with its own weight matrix and bias, so its parameter count is roughly four times that of one dense transformation of the same size.

Does this include normalization layer parameters?

No, this calculates only the specified layer type. BatchNorm/LayerNorm add a small number of additional parameters (typically 2 × channels) not included here.

How do I estimate a full model's parameter count?

Sum the parameter counts of every layer in the architecture. For transformer models specifically, see the Transformer Parameters Calculator for a purpose-built formula.

Related Calculators

Parameter Count Calculator – Calculate Total Parameters