Keras: “must compile model before using it” despite compile() is used

Question

I want to create and train a CNN model in Keras for classification of banknotes. Creating models works fine with simple tutorials but not with the architecture I adopt from

Answer 1

If ever someone ends up with the same error code here is maybe a way to fix it. So I was using a generator and was getting the "Must compile" error even tho everything was fine. I was able to fix it by doing a model.fit(x,y) on a single batch before launching my fit_generator and everything worked fine after that. I don't know if this helps anyone but yeah!

Answer 2

Try This:

from keras.optimizers import Adam
opt = keras.optimizers.Adam(use your own learning rate)
model.compile(optimizer=opt, loss="categorical_crossentropy", metrics=model.compile(optimizer=opt, loss="categorical_crossentropy", metrics=['accuracy']))

Answer 3

You can run evaluate on a small set and that would fix it.

Answer 4

Found my mistake - explanation for future reference.

The error origniates back in compile() where the first if-statement says:

if not self.built:
    # Model is not compilable because
    # it does not know its number of inputs
    # and outputs, nor their shapes and names.
    # We will compile after the first
    # time the model gets called on training data.
return

So I specified input_shape= and input_format=in the first Conv2D layer and everything works fine.