TypeError: ('Keyword argument not understood:', 'input') of ResNet

Question

This code:

input_tensor = Input(shape=(input_width, input_height, 3))
ResNet50 = ResNet50(include_top=False, weights='imagenet',input_tensor=input_tensor)
top_model = Sequential()
top_model.add(Flatten(input_shape=ResNet50.output_shape[1:]))
top_model.add(Dense(8, activation='softmax'))
model = Model(input=ResNet50.input, output=top_model(ResNet50.output))
model.compile(loss='categorical_crossentropy',
              optimizer=optimizers.SGD(lr=1e-3, momentum=0.9),
              metrics=['accuracy'])

causes TypeError:

TypeError                                 Traceback (most recent call last)

<ipython-input-41-07033765de09> in <module>()
     58 top_model.add(Flatten(input_shape=ResNet50.output_shape[1:]))
     59 top_model.add(Dense(8, activation='softmax'))
---> 60 model = Model(input=ResNet50.input, output=top_model(ResNet50.output))
     61 model.compile(loss='categorical_crossentropy',
     62               optimizer=optimizers.SGD(lr=1e-3, momentum=0.9),

2 frames

/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/utils/generic_utils.py in validate_kwargs(kwargs, allowed_kwargs, error_message)
    776   for kwarg in kwargs:
    777     if kwarg not in allowed_kwargs:
--> 778       raise TypeError(error_message, kwarg)
    779 
    780 

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

How should I fix it?

• tensorflow version: 2.3.0
• keras version: 2.4.3

Answer 1

As Dr. Snoopy mentioned in the comment the parameters are called 'inputs' and 'outputs' with the 's':

model = Model(inputs=inputs, outputs=x)