Image_segmentation_Unet_v2 -GRADED FUNCTION: conv_block

I am getting this error:
NameError Traceback (most recent call last)
in
1 input_size=(96, 128, 3)
2 n_filters = 32
----> 3 inputs = Input(input_size)
4 cblock1 = conv_block(inputs, n_filters * 1)
5 model1 = tf.keras.Model(inputs=inputs, outputs=cblock1)

NameError: name ‘Input’ is not defined

Block 2:
[‘InputLayer’, [(None, 96, 128, 3)], 0]
[‘Conv2D’, (None, 96, 128, 1024), 28672, ‘same’, ‘relu’, ‘HeNormal’]
[‘Conv2D’, (None, 96, 128, 1024), 9438208, ‘same’, ‘relu’, ‘HeNormal’]
[‘Dropout’, (None, 96, 128, 1024), 0, 0.1]
[‘MaxPooling2D’, (None, 48, 64, 1024), 0, (2, 2)]
Test failed
Expected value

[‘Conv2D’, (None, 96, 128, 1024), 28672, ‘same’, ‘relu’, ‘He_Normal’]

does not match the input value:

[‘Conv2D’, (None, 96, 128, 1024), 28672, ‘same’, ‘relu’, ‘HeNormal’]

AssertionError Traceback (most recent call last)
in
30 print(layer)
31
—> 32 comparator(summary(model2), output2)

/tf/W3A2/test_utils.py in comparator(learner, instructor)
17 “\n\n does not match the input value: \n\n”,
18 colored(f"{a}", “red”))
—> 19 raise AssertionError(“Error in test”)
20 print(colored(“All tests passed!”, “green”))
21

AssertionError: Error in test

I have not hardcoded any parameter in the Conv2D or Drop or MaxPooling2D
The output of block 2 is also as expected but still it gives error

I think I answered this in another thread. The unit test seems to have been modified to use “He_Normal”. That’s wrong.

Thx - That has solved the problem.