Table for neural network regression

I made a table for neural network regression,

regNet = trainNetwork(trData,'Percent',layers,options), and gor the following error

Error using trainNetwork (line 165)

Invalid training data table for regression. Predictors must be in the first column of the table, as a cell array of image paths or images.

The Table, .txt file, I made has two variables, a string and a double, The first two rows looks like this. I thought they look exactly as in the tutorial .

fileNames,Percent

C:\Users\181620\SCF\iMEC\Data\regData\s7_x8y28_x8500y2800_1_1.png,68.6

C:\Users\181620\SCF\iMEC\Data\regData\s7_x8y28_x8500y2800_1_2.png,68.6

Answer 1

[Sourav Bairagya]

To retrieve the data from the text file, you can use “readtable” function in this way:

tbl=readtable('test.txt','Format','%s%f');

This will save the data in the desired format.

In “trainNetwork” function, you can provide a table as input but in this table first column[KP1] should contain the ‘Predictor’ information corresponding to each observation. Here, each row corresponds to each separate observation. Now, Predictor can be absolute/relative file path to an image, specified as a character vector or any image specified as a 3D numeric array. 2nd input is the ‘responseName’ which is in this case is ‘Percent’.

Now, after defining your network (“layers”) and training options (“options”) you can use this:

net = trainNetwork(tbl,'Percent',layers,options);

[Shin-yee Lu]

Add format to read table solved the problem. Thanks