InvalidArgumentError: The node has inputs from different frames

Question

I was playing around with Tensorflow and ran into a problem with this code:

def process_tree_tf(matrix, weights, idxs, name=None):

    with tf.name_scope(na         


        

Answer 1

You can initialize biases inside the loop_body, like this:

 def loop_body(loop_idx, mat, idxs, weights):
     x = mat[loop_idx]
     w = weights
     bias = tf.get_variable(dtype=tf.float64,
                            shape=[2],
                            initializer=tf.constant_initializer(value=np.array([0.1,0.1]), dtype=tf.float64))

You said that you've tried tf.get_variable and tf.constant_initializer, I'm wondering whether you've found another solution?

Answer 2

This is actually a subtle issue with tf.Variable objects in TensorFlow's tf.while_loop(). TensorFlow becomes confused because it appears that the tf.constant() with which you're initializing the variable is a value created inside the loop (even though it's clearly loop invariant), but all variables get hoisted outside the loop. The easiest resolution is to move the creation of the variable outside the loop:

def process_tree_tf(matrix, weights, idxs, name=None):

    with tf.name_scope(name, "process_tree", [tree, weights, idxs]).as scope():
         loop_index = tf.sub(tf.shape(matrix)[0], 1)
         loop_vars = loop_index, matrix, idxs, weights

         # Define the bias variable outside the loop to avoid problems.
         bias = tf.Variable(tf.constant(0.1, [2], dtype=tf.float64)) 

         def loop_condition(loop_idx, *_):
             return tf.greater(loop_idx, 0)

         def loop_body(loop_idx, mat, idxs, weights):
             x = mat[loop_idx]
             w = weights

             # You can still refer to `bias` in here, and the loop body
             # will capture it appropriately.
             ...
             return loop_idx-1, mat, idxs, weights

         return tf.while_loop(loop_condition, loop_body, loop_vars, name=scope)[1]

(Another possible resolution would be to use a tf.constant_initializer() rather than a tf.constant() when creating the variable.)