File Exchange

image thumbnail

Deep Learning Toolbox Model for DenseNet-201 Network

Pretrained DenseNet-201 network model for image classification


Updated 16 Sep 2020

DenseNet-201 is a pretrained model that has been trained on a subset of the ImageNet database. The model is trained on more than a million images and can classify images into 1000 object categories (e.g. keyboard, mouse, pencil, and many animals).

Opening the densenet201.mlpkginstall file from your operating system or from within MATLAB will initiate the installation process for the release you have.

This mlpkginstall file is functional for R2018a and beyond.

Usage Example:

% Access the trained model
net = densenet201();

% See details of the architecture

% Read the image to classify
I = imread('peppers.png');

% Adjust size of the image
sz = net.Layers(1).InputSize
I = I(1:sz(1),1:sz(2),1:sz(3));

% Classify the image using DenseNet-201
label = classify(net, I)

% Show the image and the classification results

Comments and Ratings (4)

Kyle Peterson

Can this model be used with the compiler?

Abhijit Roy


Need an example for image segmentation.

Redha Almahdi

MATLAB Release Compatibility
Created with R2018a
Compatible with R2018a to R2020b
Platform Compatibility
Windows macOS Linux