silly error in trainnet network design

4 views (last 30 days)
Raf
Raf on 11 Sep 2024
Edited: Drew on 11 Sep 2024
received following errors - for seemingly straight forward command:
> net = trainnet(data1, class1, net_1, "crossentropy", options);
Error Number of observations in predictors (1) and targets (1071) must match.
Check that the data and network are consistent.
This is odd because both the training and validation data/class are matching size 1071 X 140 and 1071 X 1. Could you please advise. Similarly validation in options have compatiable digmensions. weird.

Accepted Answer

Drew
Drew on 11 Sep 2024
Edited: Drew on 11 Sep 2024
The error message indicates that there is just one (1) observation, but 1071 targets. Check the data type and size of the inputs. See the doc https://www.mathworks.com/help/deeplearning/ref/trainnet.html for details about the several types of data that can be input, and for options like "InputDataFormats" which can affect the interpretation of the inputs.
If this answer helps you, please remember to accept the answer.
  2 Comments
Raf
Raf on 11 Sep 2024
spot on, been a while, data was entered as matrices, converted to cells working like a champ. Thanks. RA
Drew
Drew on 11 Sep 2024
I'm glad to hear that it is working now. I see there is an upvote on the answer, but it looks like you have not accepted the answer. Do you see the button to accept the answer?

Sign in to comment.

More Answers (0)

Categories

Find more on Image Data Workflows in Help Center and File Exchange

Products


Release

R2024a

Community Treasure Hunt

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

Start Hunting!