Hi Mentor, For the case from_logits=True and having linear activation in the output layer, our doubt is how the sparse categorical cross entropy loss function computing softmax at the loss function ? Also for the similar case of from_logits=True and linear activation in the output layer, how the…

Numerical correct implementation of softmax

rmwkwok December 24, 2022, 3:16pm 3

You may also want to read this post!

Raymond

1 Like

Topic		Replies	Views
Bug in TensorFlow project Improving Deep Neural Networks: Hyperparameter tun coursera-platform	11	583	August 28, 2021
CNN Week1 2nd Assignment - 'categorical_crossentropy' applied twice? Convolutional Neural Networks coursera-platform	3	651	April 13, 2023
Softmax implementation Advanced Learning Algorithms week-module-2	6	531	May 11, 2023
Activation function of SoftMax after optimization Advanced Learning Algorithms week-module-2	5	414	July 23, 2023
C3W2, assignment - Exercise 4 - masked_loss() NLP with Sequence Models week-module-2	1	300	May 12, 2024