search

sdemyanov / ConvNet

Convolutional Neural Networks for Matlab for classification and segmentation, including Invariang Backpropagation (IBP) and Adversarial Training (AT) algorithms. Trained on GPU, require cuDNN v5.
240 stars 141 forks source link

Training my network #30

Open Source82 opened 8 years ago

Source82 commented 8 years ago

Hi,

Forgive me if am asking a question that is too simple (am new to deep learning).

Please, which mat file should one edit if he wants to train his own classifier.

Is it cnnexamples.m or train_mnist.m

Furthermore, I was just wondering for face recognition are 100 examples per class sufficient for the training?

Thanks

HosnaCSE commented 8 years ago

Hello, Could you able to run the original code. I am struggling with downloaded one (I am also beginner) .I just trying to compile downloaded code using CPU, but get the error as follows:

Error using genweights_mex Assertion Failed: In 'mexGetScalar' mx_array is not numeric

Error in genweights (line 4) weights = genweights_mex(layers, params);

Error in cnnexamples (line 82) weights = single(genweights(layers, params, funtype));

If you run downloaded code successfully, can you please help me to resolve this error?