If I reshape one_hot to (depth), the one_hot_matrix_test() is happy, but new_y_test = y_test.map(one_hot_matrix) is not, producing a long stack of grief followed by ValueError: Shape must be rank 1 but is rank 0 for ‘{{node Reshape}} = Reshape[T=DT_FLOAT, Tshape=DT_INT32](one_hot, Reshape/shape)…

No good solution for one_hot_matrix

nramon August 7, 2021, 9:46am 5

Here’s the explanation

2 Likes

Topic		Replies	Views
Course 2, Week 3, one_hot_matrix error Improving Deep Neural Networks: Hyperparameter tun	3	619	August 28, 2021
One-hot encoding Improving Deep Neural Networks: Hyperparameter tun	5	577	January 26, 2022
Tensorflow_introduction one_hot_matrix_test Error Improving Deep Neural Networks: Hyperparameter tun	8	642	August 17, 2021
C2_W3 one_hot - tests successfully but failed to evaluate "y_test" Improving Deep Neural Networks: Hyperparameter tun week-3	2	98	June 19, 2024
Course 2 Week 3 one_hot_matrix error Improving Deep Neural Networks: Hyperparameter tun	5	808	September 2, 2021