# Face \_Recognition **URL:** \ **Category:** Convolutional Neural Networks\ **Tags:** coursera-platform\ **Created:** [August 5, 2021, 7:34pm UTC](https://community.deeplearning.ai/t/face-recognition/25427 "2021-08-05T19:34:57Z")\ **Posts on this page:** 2\ **Page:** 1
**Author:** ![ano\_11](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/ano_11/32/131645_2.png) [@ano\_11](https://community.deeplearning.ai/u/ano_11)\ **Post date:** [August 5, 2021, 7:34pm UTC](https://community.deeplearning.ai/t/face-recognition/25427/1 "2021-08-05T19:34:57Z")
What is the error here? ## loss = tf.Tensor(527.2598, shape=(), dtype=float32) TypeError Traceback (most recent call last) in 11 12 y\_pred\_perfect = ([1., 1.], [1., 1.], [1., 1.,]) —\> 13 loss = triplet\_loss(y\_true, y\_pred\_perfect, 5) 14 assert loss == 5, “Wrong value. Did you add the alpha to basic\_loss?” 15 y\_pred\_perfect = ([1., 1.],[1., 1.], [0., 0.,]) in triplet\_loss(y\_true, y\_pred, alpha) 22 #(≈ 4 lines) 23 # Step 1: Compute the (encoding) distance between the anchor and the positive —\> 24 pos\_dist = tf.reduce\_sum(tf.square(anchor - positive), axis = -1) 25 # Step 2: Compute the (encoding) distance between the anchor and the negative 26 neg\_dist = tf.reduce\_sum(tf.square(anchor - negative), axis = -1) TypeError: unsupported operand type(s) for -: ‘list’ and ‘list’ ---
**Author:** ![TMosh](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/tmosh/32/9321_2.png) [@TMosh](https://community.deeplearning.ai/u/TMosh)\ **Post date:** [August 6, 2021, 12:10am UTC](https://community.deeplearning.ai/t/face-recognition/25427/2 "2021-08-06T00:10:02Z")
The error suggests that subtracting two lists “(anchor - positive)” is not allowed in python. Try the “tf.subtract()” function instead.