small fix

  def build(self):

    # Create target inputs

    self.label_placeholder = Input(tensor=K.placeholder(

      shape=(None,self.n_tasks), name="label_placeholder", dtype='bool'))

      shape=(None,self.n_tasks), name="label_placeholder", dtype='float32'))

    self.weight_placeholder = Input(tensor=K.placeholder(

          shape=(None,self.n_tasks), name="weight_placholder", dtype='float32'))

    for task in range(self.n_tasks):

      task_label_vector = task_labels[task]

      task_weight_vector = task_weights[task]

      task_loss = loss_fn(outputs[task], task_label_vector,

                          task_weight_vector) 

      task_loss = loss_fn(outputs[task], tf.squeeze(task_label_vector),

                          tf.squeeze(task_weight_vector)) 

      task_losses.append(task_loss)

    # It's ok to divide by just the batch_size rather than the number of nonzero

    # examples (effect averages out)

    featurizer = dc.feat.CircularFingerprint(size=1024)

  elif featurizer == 'GraphConv':

    featurizer = dc.feat.ConvMolFeaturizer()

  loader = dc.data.DataLoader(

  loader = dc.data.CSVLoader(

      tasks=delaney_tasks, smiles_field="smiles", featurizer=featurizer)

  dataset = loader.featurize(

      dataset_file, shard_size=8192)

  with tf.Session() as sess:

    model = dc.models.MultitaskGraphRegressor(

      sess, graph_model, len(delaney_tasks), batch_size=batch_size,

      learning_rate=1e-2, learning_rate_decay_time=1000,

      learning_rate=1e-3, learning_rate_decay_time=1000,

      optimizer_type="adam", beta1=.9, beta2=.999)

    # Fit trained model