Week 3, ex. 3 one hot matrix problem

Course Q&A Deep Learning Specialization Improving Deep Neural Networks: Hyperparameter tun
1

Hi, I am getting the following assertion error for one hot when I pass reshape and reshape when I pass one hot. I’m writing
one_hot = tf.reshape(tf.one_hot(label, depth = C, axis = 0), shape = [C , 1])

image
image708×361 11.9 KB

2

Expected output shape is (4,) but yours is (4, 1), because you are doing shape = [C , 1]). Removing that 1 would resolve the issue.