AttributeError: 'NoneType' object has no attribute 'inbound_nodes'

[liuchuanloong]

when I define a new loss function like this

    `    def batch_all_triplet_loss(X):
    # Get the pairwise distance matrix
    print('22')
    labels, embeddings = X
    print('1')
    margin = 1.0
    pairwise_dist = _pairwise_distances(embeddings, squared=False)
    # shape (batch_size, batch_size, 1)
    anchor_positive_dist = tf.expand_dims(pairwise_dist, 2)
    assert anchor_positive_dist.shape[2] == 1, "{}".format(anchor_positive_dist.shape)`
    # shape (batch_size, 1, batch_size)
    anchor_negative_dist = tf.expand_dims(pairwise_dist, 1)
    assert anchor_negative_dist.shape[1] == 1, "{}".format(anchor_negative_dist.shape)

    # Compute a 3D tensor of size (batch_size, batch_size, batch_size)
    # triplet_loss[i, j, k] will contain the triplet loss of anchor=i, positive=j, negative=k
    # Uses broadcasting where the 1st argument has shape (batch_size, batch_size, 1)
    # and the 2nd (batch_size, 1, batch_size)
    triplet_loss = anchor_positive_dist - anchor_negative_dist + margin

    # Put to zero the invalid triplets
    # (where label(a) != label(p) or label(n) == label(a) or a == p)
    mask = _get_triplet_mask(labels)
    mask = tf.to_float(mask)
    triplet_loss = tf.multiply(mask, triplet_loss)

    # Remove negative losses (i.e. the easy triplets)
    triplet_loss = tf.maximum(triplet_loss, 0.0)

    # add my loss
    triplet_loss = tf.multiply(0.5,triplet_loss)

    # Count number of positive triplets (where triplet_loss > 0)
    valid_triplets = tf.to_float(tf.greater(triplet_loss, 1e-16))
    num_positive_triplets = tf.reduce_sum(valid_triplets)
    # num_valid_triplets = tf.reduce_sum(mask)
    # fraction_positive_triplets = num_positive_triplets / (num_valid_triplets + 1e-16)

    # Get final mean triplet loss over the positive valid triplets
    triplet_loss = tf.reduce_sum(triplet_loss) / (num_positive_triplets + 1e-16)
    # return triplet_loss, fraction_positive_triplets
    return triplet_loss`

and i merge it

`    triplet_losses = merge([label, final_rmac_a],
        mode=batch_all_triplet_loss,
        name='loss',
        output_shape=(1,))

rmac_model = Model(
    inputs=[image_a, roi_a],
    outputs=triplet_losses)`

label label = Input(shape=(batch_size,)) final_rmac_a final_rmac_a = BatchNormalization()(rmac_a) why raise this wrong tips? i guess due to the keras version