Right now all initializers return TT objects and we can set the variable with them. TF likes when initializers are functions which can generate tensor on demand (like tf.contrib.layers.xavier_initializer), this way we may avoid potential problems with things like tf.while_loop
Right now all initializers return TT objects and we can set the variable with them. TF likes when initializers are functions which can generate tensor on demand (like tf.contrib.layers.xavier_initializer), this way we may avoid potential problems with things like tf.while_loop