double 'connected to' problem

lesson3.ipynb

Hi, I am experiencing this same problem. I have seen the discussion between you and Jeremy on the forums:

Jeremy: You didn't pop the last layer and replace it with one with the correct number of outputs, prior to creating conv_model. I'm not sure why it is happening - but my guess is that that's the cause. Keras often gets confused when copying layers between models - recently I've started writing code that instead copies the layer config and weights separately.

You: Got it working. Copying the config and the weights separately did the trick. Thanks!

However, I don't understand what is meant here. How do I copy the config? Do I need to create the model from scratch, i.e. add all the layers in Keras, in that case how to handle vgg_preprocess?

I have tried simply using the existing model and deleting all layers after the first conv layer i.e.

num_del = len(layers) - last_conv_idx - 1
for i in range (0, num_del):  model.pop()

(Note I create the FC model first so i don't lose the fc weights) This seems to produce the correct conv model as the weights are intact. But I'm very interested to know what yours/Jeremy's solution is.

Thanks for any help