Is there a problem with MobileNet -in keras applications- with its input shape?

[pedghz]

I am trying to implement number of networks using Keras applications. Here I am attaching a piece of code and this code works fine for ResNet50 and VGG16 but when it comes to MobileNet it generate the error:

ValueError: Error when checking target: expected dense_1 to have 4 dimensions, but got array with shape (24, 2)

# basic_model = ResNet50()
# basic_model = VGG16()
basic_model = MobileNet()
classes = list(iter(train_generator.class_indices))
basic_model.layers.pop()
for layer in basic_model.layers[:25]:
    layer.trainable = False
last = basic_model.layers[-1].output
temp = Dense(len(classes), activation="softmax")(last)

fineTuned_model = Model(basic_model.input, temp)
fineTuned_model.classes = classes
fineTuned_model.compile(optimizer=Adam(lr=0.0001), loss='categorical_crossentropy', metrics=['accuracy'])
fineTuned_model.fit_generator(
        train_generator,
        steps_per_epoch=3764 // batch_size,
        epochs=100,
        validation_data=validation_generator,
        validation_steps=900 // batch_size)
fineTuned_model.save('mobile_model.h5')

[titu1994]

This is because MobileNets uses pointwise Conv2D to classify the images (Instead of Dense), and then reshapes the 2D output to 1D as expected in Dense.

You have two choices - 1) pop 3 times, add Dense and then Flatten layer. 2) pop 5 times, add Dropout and then Dense.

To look at why you need so many pop operations, refer to the actual code of MobileNets - beginning from line 485