Exercise 1 - happyModel

Course Q&A Deep Learning Specialization Convolutional Neural Networks
1

Hi
I have written this code for the happy model, but it didn’t work. Additionally, because the function has no input I was confused. What should I do?

Error:
File “”, line 34
input_shape = tf.keras.input(shape=(64,64,3))
^
SyntaxError: invalid syntax

2

The error is before the input shape line. Check for any accidental edits.

3

There is not anything before this, this is all the code

4

Every layer you define within the square brackets must end with a comma. You are creating a list of layers.

5

And you do not need any of the equal signs or the temp variables. Nothing on the left at all. You are just creating a list of layers.

You do need “model =”, but none of the others.

Please edit your message and remove the code.

1 Like
6

Thanks for your responsibilty.
I edited the code as below:

model = tf.keras.Sequential([
        # YOUR CODE STARTS HERE
         tfl.ZeroPadding2D(padding=3,input_shape=(64,64,3)),
         tfl.Conv2D(kernel_size=(7,7),filters=32,strides=1),
         tfl.BatchNormalization(axis=3),
         tfl.ReLU,
         tfl.MaxPool2D,
         tfl.Flatten,
         tfl.Dense(units=1,activation='sigmoid')
        # YOUR CODE ENDS HERE
    ])

but I still get this failure:

TypeError Traceback (most recent call last)
in
----> 1 happy_model = happyModel()
2 # Print a summary for each layer
3 for layer in summary(happy_model):
4 print(layer)
5

in happyModel()
39 tfl.MaxPool2D,
40 tfl.Flatten,
—> 41 tfl.Dense(units=1,activation=‘sigmoid’)
42 # YOUR CODE ENDS HERE
43 ])

/opt/conda/lib/python3.7/site-packages/tensorflow/python/training/tracking/base.py in _method_wrapper(self, *args, **kwargs)
455 self._self_setattr_tracking = False # pylint: disable=protected-access
456 try:
→ 457 result = method(self, *args, **kwargs)
458 finally:
459 self._self_setattr_tracking = previous_value # pylint: disable=protected-access

/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/sequential.py in init(self, layers, name)
140 layers = [layers]
141 for layer in layers:
→ 142 self.add(layer)
143
144 @property

/opt/conda/lib/python3.7/site-packages/tensorflow/python/training/tracking/base.py in _method_wrapper(self, *args, **kwargs)
455 self._self_setattr_tracking = False # pylint: disable=protected-access
456 try:
→ 457 result = method(self, *args, **kwargs)
458 finally:
459 self._self_setattr_tracking = previous_value # pylint: disable=protected-access

/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/sequential.py in add(self, layer)
180 raise TypeError('The added layer must be ’
181 'an instance of class Layer. ’
→ 182 'Found: ’ + str(layer))
183
184 tf_utils.assert_no_legacy_layers([layer])

TypeError: The added layer must be an instance of class Layer. Found: <class ‘tensorflow.python.keras.layers.advanced_activations.ReLU’>

I am learning Keras but I have no clue how to get this issue sorted

1 Like
7

Maybe try adding () after ReLU, MaxPool2D, and Flatten, to indicate that those are functions.

1 Like
8

So thankful for your response. My problem is solved.

9

I think or you have to do the below
tfl.ReLU(),
tfl.MaxPool2D(),
tfl.Flatten(）,

1 Like
10

Yeah, thanks for your helpful soloution. It was right.