Table for neural network regression

2 views (last 30 days)
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

Accepted Answer

Sourav Bairagya
Sourav Bairagya on 23 Aug 2019
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);
  1 Comment
Shin-yee Lu
Shin-yee Lu on 26 Aug 2019
Add format to read table solved the problem. Thanks

Sign in to comment.

More Answers (0)

Products


Release

R2019a

Community Treasure Hunt

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

Start Hunting!