ValueError in mulit-task network: Shape must be rank 0 but is rank 1

Question

I want to implement a Tensorflow version of a mulit-task network, based on this caffe implementation.

The networks is visualized as this tensorflow graph, but I get an

Answer 1

You declared the learning rate as a 1D Tesnor while it should be a scalar: learning_rate = tf.placeholder(tf.float64, shape=[], name="lr").