Compute Conv2D parameter counts

Quick Overview

This question evaluates understanding of convolutional neural network parameterization, specifically how kernel dimensions, input/output channels and an optional bias term determine the number of learnable parameters.

Compute Conv2D parameter counts

Company: Tesla

Role: Machine Learning Engineer

Category: Machine Learning

Difficulty: easy

Interview Round: Technical Screen

For a 2D convolution layer, given input channels C_in, output channels C_out, kernel size (k_h, k_w), stride (s_h, s_w), padding (p_h, p_w), and an optional bias term, compute the total number of learnable parameters for the layer in both cases: with bias and without bias.

Overview: This question evaluates understanding of convolutional neural network parameterization, specifically how kernel dimensions, input/output channels and an optional bias term determine the number of learnable parameters.

|Home/Tesla/Machine Learning
Tesla logo
Tesla
Sep 6, 2025
easyMachine Learning EngineerTechnical ScreenMachine Learning
31
0

Parameter Count for a 2D Convolution Layer

You are given a standard 2D convolution layer with:

  • Input channels: C_in
  • Output channels: C_out
  • Kernel size: (k_h, k_w)
  • Stride: (s_h, s_w)
  • Padding: (p_h, p_w)
  • Optional bias term

Task:

  1. Compute the total number of learnable parameters when the layer includes a bias term.
  2. Compute the total number of learnable parameters when the layer has no bias term.

Assume a standard convolution (groups = 1).

Browse More Questions

More Machine Learning•More Tesla•More Machine Learning Engineer•Tesla Machine Learning Engineer•Tesla Machine Learning•Machine Learning Engineer Machine Learning