Shape error when fitting my data to VGG16 cnn --Keras

Question

I want to classify dog breed using data augmentation and transfer learning using VGG16 as the cnn.

First I'm doing some data augmentation using ImageDataGenerator from keras

train_datagen = ImageDataGenerator(rotation_range = 30,
                               width_shift_range = 0.2,
                               height_shift_range = 0.2,
                               rescale = 1./255,
                               shear_range = 0.2,
                               zoom_range = 0.2,
                               horizontal_flip = True,
                               fill_mode = 'nearest')

train_generator = train_datagen.flow_from_directory('../data/train/',
                                                target_size = (224, 224),
                                                batch_size = batch_size,
                                                class_mode = 'categorical')

The flow_from_directory method returns a DirectoryIterator yielding tuples of (x, y) where x is a numpy array containing a batch of images with shape (batch_size, *target_size, channels) and y is a numpy array of corresponding labels. Since here the class_mode is caterogical, it's supposed to return 2D one-hot encoded labels for y.

Then I do transfer learning removing only the last layer replacing it with a dense layer with a softmax activation.

model = VGG16(weights="imagenet", include_top=False, input_shape=(224, 224, 3))

for layer in model.layers:
    layer.trainable = False

x = model.output

predictions = Dense(120, activation='softmax')(x)

new_model = Model(inputs=model.input, outputs=predictions)

Then I fit my data to the model :

new_model.fit_generator(train_generator,
                        steps_per_epoch = 6680 // batch_size,
                        epochs = 50,
                        validation_data = validation_generator,
                        validation_steps = 835 // batch_size,
                        verbose=2)

And I get the error : ValueError: Error when checking target: expected dense_3 to have 4 dimensions, but got array with shape (16, 120)

I have no idea where the problem comes from :(

Thanks for your help !

Answer 1

The summary of VGG16 gives:

Layer (type)                 Output Shape              Param #   
=================================================================
input_1 (InputLayer)         [(None, 224, 224, 3)]     0         
_________________________________________________________________
block1_conv1 (Conv2D)        (None, 224, 224, 64)      1792      
_________________________________________________________________
block1_conv2 (Conv2D)        (None, 224, 224, 64)      36928     
_________________________________________________________________
block1_pool (MaxPooling2D)   (None, 112, 112, 64)      0         
_________________________________________________________________
block2_conv1 (Conv2D)        (None, 112, 112, 128)     73856     
_________________________________________________________________
block2_conv2 (Conv2D)        (None, 112, 112, 128)     147584    
_________________________________________________________________
block2_pool (MaxPooling2D)   (None, 56, 56, 128)       0         
_________________________________________________________________
block3_conv1 (Conv2D)        (None, 56, 56, 256)       295168    
_________________________________________________________________
block3_conv2 (Conv2D)        (None, 56, 56, 256)       590080    
_________________________________________________________________
block3_conv3 (Conv2D)        (None, 56, 56, 256)       590080    
_________________________________________________________________
block3_pool (MaxPooling2D)   (None, 28, 28, 256)       0         
_________________________________________________________________
block4_conv1 (Conv2D)        (None, 28, 28, 512)       1180160   
_________________________________________________________________
block4_conv2 (Conv2D)        (None, 28, 28, 512)       2359808   
_________________________________________________________________
block4_conv3 (Conv2D)        (None, 28, 28, 512)       2359808   
_________________________________________________________________
block4_pool (MaxPooling2D)   (None, 14, 14, 512)       0         
_________________________________________________________________
block5_conv1 (Conv2D)        (None, 14, 14, 512)       2359808   
_________________________________________________________________
block5_conv2 (Conv2D)        (None, 14, 14, 512)       2359808   
_________________________________________________________________
block5_conv3 (Conv2D)        (None, 14, 14, 512)       2359808   
_________________________________________________________________
block5_pool (MaxPooling2D)   (None, 7, 7, 512)         0         
=================================================================
Total params: 14,714,688
Trainable params: 14,714,688
Non-trainable params: 0
_________________________________________________________________

The last layer has 3-d features, you need to flatten it before applying Dense and softmax.

Add a Flatten() before the last Dense layer.

x = model.output

x = Flatten()(x) # add this line

predictions = Dense(120, activation='softmax')(x)