File Exchange

image thumbnail

CNN classifier using 1D, 2D and 3D feature vectors

version 1.0.4 (340 KB) by Selva
using CNN network with pre-extracted feature vectors instead of automatically deriving the features by itself from image.

39 Downloads

Updated 16 May 2019

View Version History

View License

CNN deep network consist of inbuilt feature extraction (flattening) layer along with classification layers. By omitting the feature extraction layer (conv layer, Relu layer, pooling layer), we can give features such as GLCM, LBP, MFCC, etc directly to CNN just to classify alone. This can be acheived by building the CNN architecture using fully connected layers alone. This is helpful for classifying audio data.

http://cs231n.github.io/convolutional-networks/ visit this page for doubts regarding the architecture. I have used C->R->F->F->F architecture

Cite As

Selva (2021). CNN classifier using 1D, 2D and 3D feature vectors (https://www.mathworks.com/matlabcentral/fileexchange/68882-cnn-classifier-using-1d-2d-and-3d-feature-vectors), MATLAB Central File Exchange. Retrieved .

Comments and Ratings (12)

BERGHOUT Tarek

thank you its was helpful.

Shubhobrata

can anyone help me with this:

I want to use the 1D CNN for unsupervised clustering. How can I use this code for the same. Please help.

NICOLE MIN

how do i input my signal?

Borui Li

I am looking for a solution to use CNN on 1-D vibration spectrum data. The code in file CNN_1D_vector_input_classifier can work. But it needs a correction on a minor problem. In the code of defining the layers, you need to change convolution2dLayer(5,16,'Padding','same') into convolution2dLayer([5 1],16,'Padding','same') which means you define a filter which has a dimension 5*1. The original code define the filter of 5*5, that is why it can not work.

Huynh Quoc Viet

maged mohamed

i got this error when i try to run the code
Error using trainNetwork (line 133)
Requested 20x18446744073709551615x16x8 (17179869184.0GB) array exceeds maximum array size
preference. Creation of arrays greater than this limit may take a long time and cause
MATLAB to become unresponsive. See array size limit or preference panel for more
information.

Error in Untitled (line 40)
net = trainNetwork(trainD,targetD',layers,options);

MShia

or how to run this tool

Mahe

I got an error when I run the 1D_vector_input_classifier. " convolution2dLayer(3,16,'Padding','same')"
trainNetwork (line 154) Padding exceeds array bounds.

Matt J

It look like this requires the Deep Learning toolbox.

KAPIL PANDIT

Selva

http://cs231n.github.io/convolutional-networks/ visit this page for doubts regarding the architecture. I have used C->R->F->F->F architecture

MATLAB Release Compatibility
Created with R2017b
Compatible with any release
Platform Compatibility
Windows macOS Linux

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!