Sigmoid function, Week 3, Improving DNN

Course Q&A Deep Learning Specialization Improving Deep Neural Networks: Hyperparameter tun
1

#######################CODE ##################################

def sigmoid(z):

"""
Computes the sigmoid of z

Arguments:
z -- input value, scalar or vector

Returns: 
a -- (tf.float32) the sigmoid of z
"""
# tf.keras.activations.sigmoid requires float16, float32, float64, complex64, or complex128.

# (approx. 2 lines)
# z = ...
# result = ...
# YOUR CODE STARTS HERE


# YOUR CODE ENDS HERE
return a

result = sigmoid(-1)
print ("type: " + str(type(result)))
print ("dtype: " + str(result.dtype))
print ("sigmoid(-1) = " + str(result))
print ("sigmoid(0) = " + str(sigmoid(0.0)))
print ("sigmoid(12) = " + str(sigmoid(12)))

def sigmoid_test(target):
result = target(0)
assert(type(result) == EagerTensor)
assert (result.dtype == tf.float32)
assert sigmoid(0) == 0.5, “Error”
assert sigmoid(-1) == 0.26894143, “Error”
assert sigmoid(12) == 0.9999939, “Error”

print("\033[92mAll test passed")

sigmoid_test(sigmoid)

################## OUTPUT #################################
type: <class ‘tensorflow.python.framework.ops.EagerTensor’>
dtype: <dtype: ‘float32’>
sigmoid(-1) = tf.Tensor(
[[0.10371852]
[0.9506831 ]
[0.25175616]
[0.30040282]], shape=(4, 1), dtype=float32)
sigmoid(0) = tf.Tensor(
[[0.10371852]
[0.9506831 ]
[0.25175616]
[0.30040282]], shape=(4, 1), dtype=float32)
sigmoid(12) = tf.Tensor(
[[0.10371852]
[0.9506831 ]
[0.25175616]
[0.30040282]], shape=(4, 1), dtype=float32)

ValueError Traceback (most recent call last)
in
16 print("\033[92mAll test passed")
17
—> 18 sigmoid_test(sigmoid)

in sigmoid_test(target)
10 assert(type(result) == EagerTensor)
11 assert (result.dtype == tf.float32)
—> 12 assert sigmoid(0) == 0.5, “Error”
13 assert sigmoid(-1) == 0.26894143, “Error”
14 assert sigmoid(12) == 0.9999939, “Error”

/opt/conda/lib/python3.7/site-packages/tensorflow/python/framework/ops.py in bool(self)
982
983 def bool(self):
→ 984 return bool(self._numpy())
985
986 nonzero = bool

ValueError: The truth value of an array with more than one element is ambiguous. Use a.any() or a.all()

################################################################

2

Looks like you are redefining z variable instead of using the argument received by the sigmoid function.

Please edit your post so that the solution code is not explicitly displayed.

I hope that gives you a hint to solve the exercise, if not and you want to share your code with me you can do it by direct message.

1 Like
3

Sir,

Thank you for the prompt response to my query.
Understood, sir.
I’ve made the changes and passed all tests.
Thank you.

I have also made the edit in the question. My apologies.

1 Like