Hello, I have implemented the previous questions of the notebook correctly, but I am struggling with the cost function. I have used the tf.keras.losses.categorical() fonction for this end, assigning the right tensors to the y_true and y_pred arguments, and reshaping the inputs tensors doing someth…

There should be no need to use “reshape” there: just transpose the logits and the labels. The other thing to note is that because we are passing “logits” as the input, meaning there is no output activation applied, you need to use the from_logits argument to the categorical loss function to tell it …

Hi Paul, Thanks so much! I followed the advice and it works perfectly :slight_smile:

in the latest lab it asks us to use tf.reduce_sum instead of tf.reduce_mean. the code only passes when you use tf.reduce_sum and dont divide by the number of total examples. This is odd as thats not how we learned to compute the cost function. Why is that?

Once you switch to minibatch gradient descent, it works better to keep the running sum of cost over all the samples in each batch. Once you have the total sum for the complete epoch by keeping the running sum over the batches, then you can divide by the number of samples in the full epoch to get the…

BTW you can see this method of handling the minibatch cost in action in the Optimization Methods assignment in Week 2 of Course 2. Note that the compute_cost function they provide in the utility function file returns the sum of the cost across the samples of the current batch.

This is very helpful, thank you!

[image] paulinpaloalto: from_logits Hi, can you please talk about it more in simpler term?

Thanks Paul, this was super helpful.

The computation of the cost function: compute_cost()

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

paulinpaloalto November 4, 2022, 2:31pm 9

Here is another thread which discusses that in more detail. Please have a look and let us know if that’s not enough.

Topic		Replies	Views
Test does not match. Did you get the reduce sum of your cost functions? Improving Deep Neural Networks: Hyperparameter tun coursera-platform	18	1098	November 15, 2022
Please help with compute total loss! Improving Deep Neural Networks: Hyperparameter tun coursera-platform	3	772	February 27, 2023
DLS 2 Week 3_Exercise_6_compute_cost()_ERROR Improving Deep Neural Networks: Hyperparameter tun coursera-platform	27	1695	August 28, 2024
Stuck on C2W3 Assignment: Cost Function Improving Deep Neural Networks: Hyperparameter tun coursera-platform	23	1187	October 3, 2023
Programming Assignment: TensorFlow Introduction Improving Deep Neural Networks: Hyperparameter tun coursera-platform	2	638	May 27, 2022

The computation of the cost function: compute_cost()

Related topics