ValueError: The last dimension of the inputs to `Dense` should be defined. Found `None`

Question

My model is defined as below:

def build(data):
    model = Sequential()
    model.add(Cropping2D(cropping=((79, 145), (50, 250)), input_shape= 
                                                                   (160,320,3)))
    model.add(Lambda(lambda x: x/127.5 - 1.0))

    model.add(Conv2D(24, (2, 2), padding='same'))
    model.add(ELU())
    model.add(Conv2D(36, (2, 2), padding='same'))
    model.add(ELU())
    model.add(Conv2D(48, (2, 2), padding='same'))
    model.add(ELU())

    # Add a flatten layer
    model.add(Flatten())
    model.summary()
    model.add(Dense(100))
    model.add(ELU())
    model.add(Dense(50))
    model.add(ELU())
    model.add(Dense(10))
    model.add(ELU())
    model.add(Dense(1))

    return model

Getting this error:

ValueError: The last dimension of the inputs to Dense should be defined. Found None.

I ran model.summary() and got the following output

Layer (type)                 Output Shape              Param #   
=================================================================
cropping2d_15 (Cropping2D)   (None, 0, 20, 3)          0         
_________________________________________________________________
lambda_23 (Lambda)           (None, 0, 20, 3)          0         
_________________________________________________________________
conv2d_47 (Conv2D)           (None, 0, 20, 24)         312       
_________________________________________________________________
elu_43 (ELU)                 (None, 0, 20, 24)         0         
_________________________________________________________________
conv2d_48 (Conv2D)           (None, 0, 20, 36)         3492      
_________________________________________________________________
elu_44 (ELU)                 (None, 0, 20, 36)         0         
_________________________________________________________________
conv2d_49 (Conv2D)           (None, 0, 20, 48)         6960      
_________________________________________________________________
elu_45 (ELU)                 (None, 0, 20, 48)         0         
_________________________________________________________________
flatten_12 (Flatten)         (None, None)              0         
=================================================================
Total params: 10,764
Trainable params: 10,764
Non-trainable params: 0

I am fairly new to python, any inputs will be appreciated.

Answer 1

You are cropping your input image too much. The cropping argument is interpreted as follows:

If tuple of 2 tuples of 2 ints: interpreted as ((top_crop, bottom_crop), (left_crop, right_crop))

Consider the following example from the Keras docs:

# Crop the input 2D images or feature maps
model = Sequential()
model.add(Cropping2D(cropping=((2, 2), (4, 4)),
                     input_shape=(28, 28, 3)))
# now model.output_shape == (None, 24, 20, 3)

In your code, you are cropping 79 pixels from the top and 145 pixels from the bottom, whereas the height of your images is only 160 pixels. With less cropping, your code runs fine, eg:

model.add(Cropping2D(cropping=((10, 10), (10, 10)), input_shape=(160,320,3)))