If I reshape the one_hot matrix to (depth, ), the tests pass. However, if I reshape the one_hot matrix to (depth, 1), the tests fail. Why is this? I thought we would need to use (depth, 1) to make sure we get a single-column matrix with rows = depth. Basically, I don’t understand why we need to use …

Because the shape of both y_pred and y_true are [batch_size, num_classes], later on, when you need to calculate the cost using tf.keras.losses.CategoricalCrossentropy | TensorFlow v2.14.0 If you reshape to [depth, 1], the shape will be [batch_size, num_classes, 1] which throws an exception in…

Sorry to ask, but, we should then, ignore this error? [image]

I don’t remember if it gives you 100% pass when you submit with that error, if it does, then you can ignore it. If it doesn’t, change it, but remember that it’s not needed here.

[image] DLS Course 2 - Wk 3 - Ex 3 One_hot_matrix - Reshape Errors Improving Deep Neural Networks: Hyperparameter tun The documentation for tf.reshape(tensor, shape, name=None) states that the shape argument must be: A Tensor. Must be one of the following types: int32,…

Here’s another explanation: shape=[C, 1]: This shape results in a column vector. Each element of the one-hot encoded tensor will be reshaped into its own column. This is often used when you want to represent each one-hot encoded label as a column vector. shape=[C,]: This shape results in a one-dim…

Course 2, Week 3, one_hot_matrix clarification

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

philgo November 24, 2021, 3:57am 5

it seems that “[depth]” works for me, not “depth”, not “…, depth,1)”, not “…,(depth,1)”.

Error mapping one_hot_matrix over y_test and y_train

DLS Course 2 - Wk 3 - Ex 3 One_hot_matrix - Reshape Errors

Topic		Replies	Views
DLS Course 2 - Wk 3 - Ex 3 One_hot_matrix - Reshape Errors Improving Deep Neural Networks: Hyperparameter tun coursera-platform	9	1081	November 14, 2022
Question of week3 programming exercise - Using One Hot Encodings question Improving Deep Neural Networks: Hyperparameter tun coursera-platform	2	572	June 23, 2022
No good solution for one_hot_matrix Improving Deep Neural Networks: Hyperparameter tun coursera-platform	4	931	August 7, 2021
Week 3, ex. 3 one hot matrix problem Improving Deep Neural Networks: Hyperparameter tun week-module-3 , coursera-platform	1	255	January 9, 2024
Course 2, Tensorflow_introduction One_hot matrix function Improving Deep Neural Networks: Hyperparameter tun coursera-platform	4	666	September 28, 2021

Course 2, Week 3, one_hot_matrix clarification

Related topics