Matlab/Octave toolbox for deep learning. Includes Deep Belief Nets, Stacked Autoencoders, Convolutional Neural Nets, Convolutional Autoencoders and vanilla Neural Nets. Each method has examples to get you started.
I‘ve met an error in running 'test_example_CNN' with my own trainning data
the code is as below:
%%
error in using cnnsetup (line 30)
Layer 3 size must be integer. Actual: -1 4623.5
I‘ve met an error in running 'test_example_CNN' with my own trainning data the code is as below: %% error in using cnnsetup (line 30) Layer 3 size must be integer. Actual: -1 4623.5
error with test_example_CNN (line 36) cnn = cnnsetup(cnn, train_x, train_y); %%
The structure of original data is: train_x: 282860000 double train_y: 1060000 double test_x: 282810000 double test_y: 1010000 double
While my own data structure is: train_x: 29251 double train_y: 19251 double test_x: 21631 double test_y: 11631 double
So what should I do now? Should I modify my data or the code?