Input to Convolution Neural Network

AP
2020 6 29
1 个回答
更新时间：2020 6 30
4 次查看（30 天）

0 个投票

I am using convolution neural network on face images of the size 1024*768*3.
I want to pass these images as input to first input layer of CNN.
what should be size of the 'inputImageLayer' for CNN?
How to decide the size of First layer of CNN?

请先登录，再回答此问题。

回答（1 个）

bharath pro
bharath pro 2020-6-29

0 个投票

The ImageInputLayer is used to take image inputs when designing a CNN. According to the documentation, it can be called using ImageInputLayer([h w c]), where c= number of chanels. I am assuming for you the height and width of images are 1024 and 768 respectively and c=3. So for this you would need to use ImageInputLayer([1024 768 3]) to instantiate this layer.

8 个评论
显示 6更早的评论 隐藏 6更早的评论

AP
AP 2020-6-30
Thank you bharat pro. I have tried with these dinensions but it is still giving me error ' Not enough input arguments '.
bharath pro
bharath pro 2020-6-30
Is the input vector a 1*3 row vector? Can you check its dimensions?
AP
AP 2020-6-30
My image has dimension height 768 width 1024 color representation sRGB.
bharath pro
bharath pro 2020-6-30
What output do you get when you run size(image)? Also the row vector has to be [768 1024 3] in your case.
AP
AP 2020-6-30
My output for size(image) is 768 1024 3. Still i am getting error saying 'inputArguments = iParseInputArguments(varargin{:});.
bharath pro
bharath pro 2020-6-30
Can you share your code here. The problem could be in the other layers as well.
AP
AP 2020-6-30
Clc;
clear all;
close all;
%read image
a = imread('tryb.jpg');
size(a)
a1 =rgb2gray(a);
%show image
figure, imshow(a1);
imageSize =[768 1024 3];
matlabroot ='D:\MY DESKTOP\IMAGE PROCESSING MATERIAL\database\for nose detect\';
Datasetpath =fullfile(matlabroot ,'cnn2','Dataset1');
Data = imageDatastore(Datasetpath,'IncludeSubfolders',true,'LabelSource','foldernames');
layers = [
imageInputLayer (imageSize)
covolution2dLayer([5 20])
reluLayer
maxPooling2dLayer(2,'stride',2)
covolution2dlayer([5 20])
reluLayer
maxPooling2dLayer(2,'stride',2)
fullyConnectedLayer(2)
softmaxLayer
ClassiifcationLayer()];
options = trainingOptions('sgdm','maxEpoch',15,'initialLearningrate , 0.001');
convnet = trainNetwork (Data,layers,options);
output = classify (convnet ,a);
bharath pro
bharath pro 2020-6-30
change your layers to this:
layers = [
imageInputLayer(imageSize,'Normalization','none')
convolution2dLayer(5,20)
reluLayer()
maxPooling2dLayer(2,'Stride',2)
convolution2dLayer(5,20)
reluLayer()
maxPooling2dLayer(2,'Stride',2)
fullyConnectedLayer(1)
softmaxLayer
classificationLayer()];
Also your options seem to be wrong. Please change that.

请先登录，再进行评论。

类别

在 帮助中心 和 File Exchange 中查找有关 Recognition, Object Detection, and Semantic Segmentation 的更多信息

标签

提问:

AP
AP
2020-6-29

评论：

bharath pro
bharath pro
2020-6-30

Community Treasure Hunt

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

Start Hunting!

Translated by