C4 W2 A2 Preprocess input type error

Course Q&A Deep Learning Specialization Convolutional Neural Networks
1

my code:

 inputs = tf.keras.Input(shape=input_shape) 
    
    # apply data augmentation to the inputs
    x = data_augmenter(inputs)
    
    # data preprocessing using the same weights the model was trained on
    x = preprocess_input(x)

output:

TypeError                                 Traceback (most recent call last)
<ipython-input-41-11ffc7a7acb3> in <module>
----> 1 model2 = alpaca_model(IMG_SIZE, data_augmentation)

<ipython-input-40-a7e00bcc0585> in alpaca_model(image_shape, data_augmentation)
     27 
     28     # apply data augmentation to the inputs
---> 29     x = data_augmenter(inputs)
     30 
     31     # data preprocessing using the same weights the model was trained on

TypeError: data_augmenter() takes 0 positional arguments but 1 was given

how do i apply the data augmentation to inputs if it is not accepting any positional arguments?

2

You declare the function assigned to another variable without parameters first, and then you use that variable as you did here instead of the function directly.

3

Right, use the helper function.

1 Like
4
  • is this correct?
# create the input layer (Same as the imageNetv2 input size)
    inputs = tf.keras.Input(shape=input_shape) 
    
    # apply data augmentation to the inputs
    x = data_augmentation
    
    # data preprocessing using the same weights the model was trained on
    x = preprocess_input(x)
  • but there is still error
WARNING:tensorflow:`input_shape` is undefined or non-square, or `rows` is not in [96, 128, 160, 192, 224]. Weights for input shape (224, 224) will be loaded as the default.
Downloading data from https://storage.googleapis.com/tensorflow/keras-applications/mobilenet_v2/mobilenet_v2_weights_tf_dim_ordering_tf_kernels_1.0_224_no_top.h5
9412608/9406464 [==============================] - 0s 0us/step
---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-16-11ffc7a7acb3> in <module>
----> 1 model2 = alpaca_model(IMG_SIZE, data_augmentation)

<ipython-input-15-4c90c4d7794f> in alpaca_model(image_shape, data_augmentation)
     30 
     31     # data preprocessing using the same weights the model was trained on
---> 32     x = preprocess_input(x)
     33 
     34     # set training to False to avoid keeping track of statistics in the batch norm layer

/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/applications/mobilenet_v2.py in preprocess_input(x, data_format)
    500 @keras_export('keras.applications.mobilenet_v2.preprocess_input')
    501 def preprocess_input(x, data_format=None):
--> 502   return imagenet_utils.preprocess_input(x, data_format=data_format, mode='tf')
    503 
    504 

/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/applications/imagenet_utils.py in preprocess_input(x, data_format, mode)
    117   else:
    118     return _preprocess_symbolic_input(
--> 119         x, data_format=data_format, mode=mode)
    120 
    121 

/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/applications/imagenet_utils.py in _preprocess_symbolic_input(x, data_format, mode)
    261   """
    262   if mode == 'tf':
--> 263     x /= 127.5
    264     x -= 1.
    265     return x

TypeError: unsupported operand type(s) for /=: 'Sequential' and 'float'
5

No, it is not correct.
You can tell because it is throwing an error.

1 Like
6

i know that, i am asking for a solution . do tell the hint if you know , not the things I already know

@saifkhanengr can you please help on this, you are the best mentor ever.

7

Hello @Rohan_Devaki!

Please note that no one will give you a solution. All mentors are the best and guide learners voluntarily.

Regarding your query, the error lies in this line.

Hint: The data_augmentation needs an input image(s). You can read more about it here.

1 Like
8
  • thankyou that error got solved , i just needed hint, not a solution

but i got new error

   # set training to False to avoid keeping track of statistics in the batch norm layer
    x = base_model(None, training=False)

what do i need to pass in First arugment to base model ? i didnt understand
output

AttributeError                            Traceback (most recent call last)
<ipython-input-16-11ffc7a7acb3> in <module>
----> 1 model2 = alpaca_model(IMG_SIZE, data_augmentation)

<ipython-input-15-87e42a440f89> in alpaca_model(image_shape, data_augmentation)
     33 
     34     # set training to False to avoid keeping track of statistics in the batch norm layer
---> 35     x = base_model(None, training=False)
     36 
     37     # add the new Binary classification layers

/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/base_layer.py in __call__(self, *args, **kwargs)
    983 
    984         with ops.enable_auto_cast_variables(self._compute_dtype_object):
--> 985           outputs = call_fn(inputs, *args, **kwargs)
    986 
    987         if self._activity_regularizer:

/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/functional.py in call(self, inputs, training, mask)
    384     """
    385     return self._run_internal_graph(
--> 386         inputs, training=training, mask=mask)
    387 
    388   def compute_output_shape(self, input_shape):

/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/functional.py in _run_internal_graph(self, inputs, training, mask)
    482       masks = self._flatten_to_reference_inputs(mask)
    483     for input_t, mask in zip(inputs, masks):
--> 484       input_t._keras_mask = mask
    485 
    486     # Dictionary mapping reference tensors to computed tensors.

AttributeError: 'NoneType' object has no attribute '_keras_mask'
9

The base_model takes the input data, the preprocess one.

10
  • ok the model2 got compiled

but there is new error

Test failed 
 Expected value 

 ['Functional', (None, 5, 5, 1280), 2257984] 

 does not match the input value: 

 ['Functional', (None, None, None, 1280), 2257984]
---------------------------------------------------------------------------
AssertionError                            Traceback (most recent call last)
<ipython-input-19-0346cb4bf847> in <module>
     10                     ['Dense', (None, 1), 1281, 'linear']] #linear is the default activation
     11 
---> 12 comparator(summary(model2), alpaca_summary)
     13 
     14 for layer in summary(model2):

~/work/W2A2/test_utils.py in comparator(learner, instructor)
     21                   "\n\n does not match the input value: \n\n",
     22                   colored(f"{a}", "red"))
---> 23             raise AssertionError("Error in test")
     24     print(colored("All tests passed!", "green"))
     25 

AssertionError: Error in test
11

Try to get the benefit of the search option to find similar threads, like this one. You may use keyword like “alpaca_model AssertionError: Error in test” or any other keywords. Update us here.

12

I have access to my course materials now. To answer the original question, this line of code should reference data_augmentation(…), not data_augmenter(…).

data_augmentation(…) is the helper function that is defined in this cell:

image
image707×256 8.19 KB

13

To expand a bit, that’s the input data after augmentation and preprocessing. It’s named ‘x’ in the notebook.

14

I think there’s a mistake in the value you are passing to base_model(…).

15

thankyou i figured it out already , thanks for your time

16

Could you reply with the root cause, so that other students might benefit?

1 Like