File Exchange

image thumbnail

Deep Learning Toolbox Model for ResNet-18 Network

Neural Network Toolbox Model for ResNet-18 Network

46 Downloads

Updated 11 Sep 2019

ResNet-18 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 resnet18.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 = resnet18();

% See details of the architecture
net.Layers

% 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 ResNet-18
label = classify(net, I)

% Show the image and the classification results
figure
imshow(I)
text(10,20,char(label),'Color','white')

Comments and Ratings (5)

Chenhang Xu

good job

Can be generated the CUDA-code via GPU coder from resnet18? I got a error: 'Code generation for
ResNet18PreprocessingLayer preprocessing is not supported.'

doaa khalil

hi
i want to pretrained Densnet 201 to classify image how i can build code

Yisi Liu

Jon Doe

MATLAB Release Compatibility
Created with R2018a
Compatible with R2018a to R2019b
Platform Compatibility
Windows macOS Linux