0

I am using alexnet, you can see the structure of the network as following:

Alexnet structure with outputs

I used the activations function in Matlab to get the features of my data from the output of conv5 layer. The output is a feature vector with a dimension 43264 for each single image (I have 14000 Images).

I did some processing on this output with no change in the dimension so it still 43264.

I want to re-enter the data to the network starting in pooling layer 5 and train the network.

As you can notice in the structure of alexnet, the input of the pooling 5 should be 13x13x256. So I changed the feature vector 43264 to 13x13x256 matrix, so the whole training set will be a cell array 14000x1 each cell has 13x13x256.

I used the following code to train the network:

net = trainNetwork (Trainingset, labels, Layers, trainingOptions)

I still has an error saying unexpected input to Pooling layer!

Any I idea please?

Thanks in advance

Many Thanks

Meme
  • 55
  • 1
  • 7
  • Any help please, I am beginner and this is the first time dealing with deep learning – Meme Nov 16 '17 at 10:52
  • The reason you aren't getting any help is that your question is really unclear. What are you trying to achieve? You say "I did some processing in this features " but don't say what they are. And maybe a quick reminder on architecture of the parts of AlexNet that are of interest to you would help you get an answer. It is a classic but I don't think many people remember to what 43264 exactly corresponds. The error you are getting just probably means that layer 16 expects inputs that are of a different size than what your "processing" outputs. – Ash Nov 18 '17 at 21:03
  • @Ash thanks for that, I have edited the question – Meme Nov 19 '17 at 18:04

0 Answers0