File Exchange

image thumbnail

Deep Learning Toolbox Model for Inception-v3 Network

Pretrained Inception-v3 network model for image classification

27 Downloads

Updated 18 Mar 2020

Inception-v3 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, has 316 layers in total, and can classify images into 1000 object categories (e.g. keyboard, mouse, pencil, and many animals).
Opening the inceptionv3.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 R2017b and beyond.
Usage Example:
% Access the trained model
net = inceptionv3();
% 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-50
label = classify(net, I)
% Show the image and the classification results
figure
imshow(I)
text(10,20,char(label),'Color','white')

Comments and Ratings (9)

Ali Najem

All google networks inceptionv3 , Xcpetion in the update of 2020 have a layer missing, when I try to use these networks, always appear the error "too many inputs".

Hi Catherine, we removed a preprocessing layer from the model. The preprocessing is now taken care of by the imageInputLayer. This shouldn't change anything. The layer is still in the support package for the new version, in case you'd like to load an old model with the layer. This should work as well. Let me know if not.

There is an error in this update. A layer is missing
Now - version of march 2020
ans =

DAGNetwork with properties:

Layers: [315×1 nnet.cnn.layer.Layer]
Connections: [349×2 table]
InputNames: {'input_1'}
OutputNames: {'ClassificationLayer_predictions'}

Before net =

DAGNetwork with properties:

Layers: [316×1 nnet.cnn.layer.Layer]
Connections: [350×2 table]
InputNames: {'input_1'}
OutputNames: {'ClassificationLayer_predictions'}

weizhi wang

I have the following error after installation of the inception model
>> inceptionv3
Error using load
Cannot read file
C:\ProgramData\MATLAB\SupportPackages\R2019b\toolbox\nnet\supportpackages\inceptionv3\data\inceptionv3.mat.

Error in inceptionv3 (line 63)
data = load(matfile);
How can I fix that, please? I checked the .mat file exists

bryant cao

RP

cui

MATLAB Release Compatibility
Created with R2017b
Compatible with R2017b to R2020a
Platform Compatibility
Windows macOS Linux