C4 W4 A1 - Error with verify function

Course Q&A Deep Learning Specialization Convolutional Neural Networks
1

Hi ,

I am getting the following error which is think is related to how I am calculating the L2 distance. I am simply doing -

dist = np.linalg.norm(encoding - database[identity])

But I also see that the output of the triplet loss function is -

loss = tf.Tensor(527.2598, shape=(), dtype=float32)

The hint says to use np.linalg.norm but one of my values is a tensor so I am unsure of the way I calculate the distance.

The entire error message is:

It’s bertrand, welcome in!

TypeError Traceback (most recent call last)
in
1 # BEGIN UNIT TEST
----> 2 assert(np.allclose(verify(“images/camera_1.jpg”, “bertrand”, database, FRmodel), (0.54364836, True)))
3 assert(np.allclose(verify(“images/camera_3.jpg”, “bertrand”, database, FRmodel), (0.38616243, True)))
4 assert(np.allclose(verify(“images/camera_1.jpg”, “younes”, database, FRmodel), (1.3963861, False)))
5 assert(np.allclose(verify(“images/camera_3.jpg”, “younes”, database, FRmodel), (1.3872949, False)))

<array_function internals> in allclose(*args, **kwargs)

/opt/conda/lib/python3.7/site-packages/numpy/core/numeric.py in allclose(a, b, rtol, atol, equal_nan)
2157
2158 “”"
→ 2159 res = all(isclose(a, b, rtol=rtol, atol=atol, equal_nan=equal_nan))
2160 return bool(res)
2161

<array_function internals> in isclose(*args, **kwargs)

/opt/conda/lib/python3.7/site-packages/numpy/core/numeric.py in isclose(a, b, rtol, atol, equal_nan)
2255 y = array(y, dtype=dt, copy=False, subok=True)
2256
→ 2257 xfin = isfinite(x)
2258 yfin = isfinite(y)
2259 if all(xfin) and all(yfin):

TypeError: ufunc ‘isfinite’ not supported for the input types, and the inputs could not be safely coerced to any supported types according to the casting rule ‘‘safe’’

Please help. thanks

2

The problem may be that either:

  • your dist value is not a real number,
  • or your door_open value is not a boolean.
3

Also note that there is no need to compute the triplet_loss value in the verify function. The code you show looks correct to me, but maybe you’re doing something else you didn’t show us.

It turns out you can use either numpy calls or TF calls in verify, as long as you are consistent and don’t mix them. I literally did both and either solution passes the notebook tests and the grader.