I try to compute the cost, here is the code i wrote cost = tf.reduce_mean(tf.math.maximum(logits,0)-logits*labels+tf.math.log(1+tf.math.exp(-abs(logits))),axis=-1) However, i got this error, The truth value of an array with more than one element is ambiguous. Use a.any() or a.all()

getting same error. Did u get the solution and can u pls help me with initilise parameters code, if possible

I think you should use the binary_crossentropy function as stated in section 3.2. Please check if that helps.

Hi kampamocha, I’m struggling with Exercise 6 - compute_cost. Can you give me any guidance in light of the following? I can see that the lales are 1 or 0, and that the logits seem to be probabilities, hence from_logits=False, but something seems to be amiss. Regards, Harry

Hi @FatHaz , You need to compute the mean over the binary_crossentropy function, please check the example shown in the initial paragraph on section 3.2. Also note the value of from_logits parameter, since this is associated to y_pred rather than labels.

Hi kampamocha Most obliged. I’d added the mean before I read your email, but the key was changing from False to True! Thank you, Harry

your were missing the other call of tf function as tf.keras.metrics.binary_crossentropy by thw way, there was other ways i found can share as below, cost = tf.reduce_mean(tf.reduce_mean(tf.maximum(logits, 0) - logits * labels + tf.math.log(1 + tf.math.exp(-abs(logits))), axis=-1))

Can some please explain why the code in the paragraph above the cost exercise, that is - cost = tf.reduce_mean(tf.keras.losses.binary_crossentropy(y_true = logits, y_pred = labels, from_logits=True)) is not working. Whereas, - cost = tf.reduce_mean(tf.reduce_mean(tf.maximum(logits, 0) - logits …

Hi, @Saransh_Jhunjhunwala . Make sure you understand the difference between y_true and y_pred and let me know if you need any hints. Check this post if you’re not sure where the second formula comes from. Good luck with the assignment :slight_smile:

[image] Saransh_Jhunjhunwala: cost = tf.reduce_mean(tf.keras.losses.binary_crossentropy(y_true = logits, y_pred = labels, from_logits=True)) Understood my mistake, Thank you

cost = tf.reduce_mean(tf.keras.losses.categorical_crossentropy(tf.transpose(labels),tf.transpose(logits),from_logits = True)) it works and in your answer, notice that y true = labels

Week3_Tensorflow IntroductionCompute cost

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

saifkhanengr April 13, 2023, 11:03pm 16

Read this where Mentor Kin @Kic explains why we need to do that.

Best,
Saif.

Topic		Replies	Views
Cannot compute_cost course 2 week 3 Improving Deep Neural Networks: Hyperparameter tun coursera-platform	90	6968	January 7, 2023
Week 3 Programming Assignment : Ex6 Computing Cost Improving Deep Neural Networks: Hyperparameter tun coursera-platform	1	762	July 13, 2021
C2W3 Exercice 6 - compute_cost Improving Deep Neural Networks: Hyperparameter tun coursera-platform	4	702	April 20, 2022
Week 3 Assignment Binary cross entropy Improving Deep Neural Networks: Hyperparameter tun coursera-platform	3	1072	May 17, 2025
Course 2 Week 3 Tensorflow coding assingnment : Exercise 4 Improving Deep Neural Networks: Hyperparameter tun coursera-platform	5	701	August 23, 2022

Week3___Tensorflow Introduction__Compute cost

Related topics

Week3_Tensorflow IntroductionCompute cost