Week 3 Assignment 2 ex1 conv_block

Hi, I think something wrong with this output. I got all test passed but it have attribute error…

Block 1:
['InputLayer', [(None, 96, 128, 3)], 0]
['Conv2D', (None, 96, 128, 32), 896, 'same', 'relu', 'HeNormal']
['Conv2D', (None, 96, 128, 32), 9248, 'same', 'relu', 'HeNormal']
['MaxPooling2D', (None, 48, 64, 32), 0, (2, 2)]
All tests passed!
---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
<ipython-input-43-a8857f337ac5> in <module>
     17 
     18 inputs = Input(input_size)
---> 19 cblock1 = conv_block(inputs, n_filters * 32, dropout_prob=0.1, max_pooling=True)
     20 model2 = tf.keras.Model(inputs=inputs, outputs=cblock1)
     21 

<ipython-input-42-e001326c4702> in conv_block(inputs, n_filters, dropout_prob, max_pooling)
     37     if max_pooling:
     38         ### START CODE HERE
---> 39         next_layer = MaxPooling2D((2,2))(conv)
     40         ### END CODE HERE
     41 

/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/base_layer.py in __call__(self, *args, **kwargs)
    980       with ops.name_scope_v2(name_scope):
    981         if not self.built:
--> 982           self._maybe_build(inputs)
    983 
    984         with ops.enable_auto_cast_variables(self._compute_dtype_object):

/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/base_layer.py in _maybe_build(self, inputs)
   2616     if not self.built:
   2617       input_spec.assert_input_compatibility(
-> 2618           self.input_spec, inputs, self.name)
   2619       input_list = nest.flatten(inputs)
   2620       if input_list and self._dtype_policy.compute_dtype is None:

/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/input_spec.py in assert_input_compatibility(input_spec, inputs, layer_name)
    164         spec.min_ndim is not None or
    165         spec.max_ndim is not None):
--> 166       if x.shape.ndims is None:
    167         raise ValueError('Input ' + str(input_index) + ' of layer ' +
    168                          layer_name + ' is incompatible with the layer: '

AttributeError: 'Dropout' object has no attribute 'shape'

There are two groups of tests in that cell.
Your code only passes the first one - the second one throws that error.
The second set of tests uses a non-zero dropout value. So that’s the part of your conv_block() function that doesn’t work correctly.

I have found the solution to that problem

It seems bad implementation of conv
Thanks very much