Valueerror When Loading A Previously Saved Retrained Vgg16 Model Using Keras

I am using the VGG16 architecture within Keras, which I have retrained to fit my needs in the following way: vgg16_model = keras.applications.vgg16.VGG16() model = Sequential() for

Solution 1:

The problem is with the line model.layers.pop(). When you pop a layer directly from the list model.layers, the topology of this model is not updated accordingly. So all following operations would be wrong, given a wrong model definition.

Specifically, when you add a layer with model.add(layer), the list model.outputs is updated to be the output tensor of that layer. You can find the following lines in the source code of Sequential.add():

output_tensor = layer(self.outputs[0])
        # ... skipping irrelevant linesself.outputs = [output_tensor]

When you call model.layers.pop(), however, model.outputs is not updated accordingly. As a result, the next added layer will be called with a wrong input tensor (because self.outputs[0] is still the output tensor of the removed layer).

This can be demonstrated by the following lines:

model = Sequential()
for layer in vgg16_model.layers:
    model.add(layer)

model.layers.pop()
model.add(Dense(3, activation='softmax'))

print(model.layers[-1].input)
# => Tensor("predictions_1/Softmax:0", shape=(?, 1000), dtype=float32)# the new layer is called on a wrong input tensorprint(model.layers[-1].kernel)
# => <tf.Variable 'dense_1/kernel:0' shape=(1000, 3) dtype=float32_ref># the kernel shape is also wrong

The incorrect kernel shape is why you're seeing an error about incompatible shapes [4096,3] versus [1000,3].

To solve the problem, simply don't add the last layer to the Sequential model.

model = Sequential()
for layer in vgg16_model.layers[:-1]:
    model.add(layer)