0

I am building a CNN model with the sequential keras API but getting the following error on line 12 (model.add(UpSampling2D((2, 2), padding='same')))

TypeError: ('Keyword argument not understood:', 'padding')

I am using Keras 2.2.4 and Tensorflow 1.12.0

Any ideas as to why this is happening?

My code is:

# Fit regression DNN model 
print("Creating/Training CNN")
model = Sequential()
model.add( Conv2D(16, (3, 3), input_shape=(128,128,1), activation='relu', padding = 'same') )
model.add(MaxPooling2D((2, 2), padding='same'))
model.add( Conv2D(8, (3, 3), activation='relu', padding='same') )
model.add(MaxPooling2D((2, 2), padding='same'))
model.add( Conv2D(8, (3, 3), activation='relu', padding='same') )
model.add(MaxPooling2D((2, 2), padding='same', name = 'grab_that'))

model.add( Conv2D(8, (3, 3), activation='relu', padding='same') )
model.add(UpSampling2D((2, 2), padding='same'))
model.add( Conv2D(8, (3, 3), activation='relu', padding='same') )
model.add(UpSampling2D((2, 2), padding='same'))
model.add( Conv2D(16, (3, 3), activation='relu', padding='same') )
model.add(UpSampling2D((2, 2), padding='same'))
model.add( Conv2D(1, (3, 3), activation='sigmoid', padding='same') )
model.compile(optimizer='adadelta', loss='binary_crossentropy', metrics=[binary_accuracy])
history = model.fit(data_train,data_train,verbose=1,epochs=1)
JayJay81
  • 203
  • 1
  • 8

1 Answers1

2

This happens because UpSampling2D layer doesn't have such parameter. Only convolutional layers have it (see docs).

Mikhail Berlinkov
  • 1,624
  • 10
  • 15