total_loss = tf.reduce_sum(tf.keras.losses.categorical_crossentropy(logits, labels, from_logits=True)) From all the details provided, this is what I understood and expected it to be the answer but I keep getting the wrong output. Whats the issue, please help!

Right! Also please check the definition of the categorical_crossentropy function. It looks like there are some other problems with how you called it. Here’s a thread with a checklist of the common problems on this function.

Thank You so much, it solved my problem, no errors

Tensorflow_introduction, compute_total_loss()

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

saifkhanengr August 20, 2023, 1:27pm 2

I think you also need to use the transpose function. Check this guide.

Topic		Replies	Views
C2W3 - TF Programming Assignment Improving Deep Neural Networks: Hyperparameter tun coursera-platform	2	509	October 3, 2023
Week3 programming assignment; compute_total_loss question Improving Deep Neural Networks: Hyperparameter tun week-module-3 , coursera-platform	12	393	January 19, 2024
Please help with compute total loss! Improving Deep Neural Networks: Hyperparameter tun coursera-platform	3	772	February 27, 2023
DLS Course2: Week 3 Exercise 6 (compute_total_loss method) Improving Deep Neural Networks: Hyperparameter tun coursera-platform	14	2047	November 2, 2023
Course 2 week 3 compute_total_loss Improving Deep Neural Networks: Hyperparameter tun week-module-3 , coursera-platform	3	445	February 4, 2024

Tensorflow_introduction, compute_total_loss()

Related topics