Step 2:  

Split the data into two parts: 1) use 70% of the data for training (52 images) and 30% for validation (to make sure that your network has been trained properly).  

clear;
clc;
close all;

mydata = imageDatastore('MerchData', ...   % load data from folder named 'MerchData'
'IncludeSubfolders',true, ...                           % Also include the subfolders (there are 5 of these for the 5 objects, cap, cube, ...)
'LabelSource','foldernames');                       % The name of the subfolders supply the "correct answer" labels
 
[mydataTrain,mydataValidation] = splitEachLabel(mydata,0.7);
  

mydataTrain and mydataValidation are now two new variables containing images for training of the network and validation.