Week 2 Exercise 8 - Wrong Value for "W"

Course Q&A Deep Learning Specialization Neural Networks and Deep Learning
1

My code passes all the questions prior to exercise 8.
I have tried it with and without “standardizing” my training data.
This is the error I am getting.

with training data standardized:

AssertionError Traceback (most recent call last)
in
----> 1 model_test(model)

~/work/release/W2A2/public_tests.py in model_test(target)
117 assert type(d[‘w’]) == np.ndarray, f"Wrong type for d[‘w’]. {type(d[‘w’])} != np.ndarray"
118 assert d[‘w’].shape == (X.shape[0], 1), f"Wrong shape for d[‘w’]. {d[‘w’].shape} != {(X.shape[0], 1)}"
→ 119 assert np.allclose(d[‘w’], expected_output[‘w’]), f"Wrong values for d[‘w’]. {d[‘w’]} != {expected_output[‘w’]}"
120
121 assert np.allclose(d[‘b’], expected_output[‘b’]), f"Wrong values for d[‘b’]. {d[‘b’]} != {expected_output[‘b’]}"

AssertionError: Wrong values for d[‘w’]. [[ 0.00131421]
[-0.00041883]
[ 0.00057307]
[ 0.00097146]] != [[ 0.00194946]
[-0.0005046 ]
[ 0.00083111]
[ 0.00143207]]

2

If your previous functions all pass the tests, that probably means that the bug is in model. The most common problems are either referencing global variables instead of the parameters that are passed in and not passing the correct parameters to optimize. Referencing global variables usually results in shape mismatch errors, so it’s more likely that your problem is in the parameters you pass to optimize. Are you “hard-coding” any of the values you pass, e.g. learning rate or number of iterations?

3

OH MY! I didn’t pass the parameters from model to optimize so it was just using optimize()'s default values.

Thanks so much.