Two full layer - Githubissues

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

Two full layer #9

Closed shandonguniversity closed 9 years ago

shandonguniversity commented 10 years ago

Hi,thanks for your work!

I have encountered a strange problem,that in order to express a more complicated

model,I use 2 fully connected layer as a classifier.But the error rate have been greatly

improved from 3.3% to 77%.

What should I do ?

yuanpu commented 10 years ago

you should train it for a longer time.