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

Question #7

Closed mnaetr closed 9 years ago

mnaetr commented 10 years ago

Hi. I'm using the ConvNet library with Matlab on medical images (2 classes: positive or negative). In the training phase I obtained the same good results that I have obtained previously with the DeepLearnToolbox but when I test the net on new images loading the weights saved during training something wrong happen: the images are classified all positive or all negative. With the DeepLearnToolbox instead, using the same test images, I have some images classified positive and some negative. What can I do?

mnaetr commented 10 years ago

I solved the problem. I made a mistake in the reinitialization of the weights. Thank you for your work!