Commit 1fa8044a authored by Bharath Ramsundar's avatar Bharath Ramsundar
Browse files

Comment out _pad_batch

parent 864e1d1a

deepchem/datasets/__init__.py

+22 −22
Original line number Diff line number Diff line
@@ -196,8 +196,8 @@ class Dataset(object): 
        y_batch = y[indices]

        w_batch = w[indices]

        ids_batch = ids[indices]

        (X_batch, y_batch, w_batch, ids_batch) = self._pad_batch(

            X_batch, y_batch, w_batch, ids_batch, shard_batch_size)

        #(X_batch, y_batch, w_batch, ids_batch) = self._pad_batch(

        #    X_batch, y_batch, w_batch, ids_batch, shard_batch_size)

        yield (X_batch, y_batch, w_batch, ids_batch)



  @staticmethod
@@ -249,26 +249,26 @@ class Dataset(object): 
      ws.append(np.array(w_b))

    return np.vstack(ws)



  def _pad_batch(self, X_b, y_b, w_b, ids_b, batch_size):

    """Fix batch to have exactly batch_size elements.

 

    Due to rounding issues, some batches will not have exactly batch_size

    elements. Handle these batches by zero padding all arrays.

    """

    n, feature_shape = np.shape(X_b)[0], np.shape(X_b)[1:]

    _, num_tasks = np.shape(y_b)

    if n == batch_size:

      return (X_b, y_b, w_b, ids_b)

    else:

      X_batch = np.zeros((batch_size,) + feature_shape)

      y_batch = np.zeros((batch_size, num_tasks))

      w_batch = np.zeros((batch_size, num_tasks))

      ids_batch = np.zeros((batch_size,), dtype=object)

      X_batch[:n] = X_b

      y_batch[:n] = y_b

      w_batch[:n] = w_b

      ids_batch[:n] = ids_b

    return X_batch, y_batch, w_batch, ids_batch

  #def _pad_batch(self, X_b, y_b, w_b, ids_b, batch_size):

  #  """Fix batch to have exactly batch_size elements.

 

  #  Due to rounding issues, some batches will not have exactly batch_size

  #  elements. Handle these batches by zero padding all arrays.

  #  """

  #  n, feature_shape = np.shape(X_b)[0], np.shape(X_b)[1:]

  #  _, num_tasks = np.shape(y_b)

  #  if n == batch_size:

  #    return (X_b, y_b, w_b, ids_b)

  #  else:

  #    X_batch = np.zeros((batch_size,) + feature_shape)

  #    y_batch = np.zeros((batch_size, num_tasks))

  #    w_batch = np.zeros((batch_size, num_tasks))

  #    ids_batch = np.zeros((batch_size,), dtype=object)

  #    X_batch[:n] = X_b

  #    y_batch[:n] = y_b

  #    w_batch[:n] = w_b

  #    ids_batch[:n] = ids_b

  #  return X_batch, y_batch, w_batch, ids_batch



  def __len__(self):

    """

deepchem/models/tensorflow_models/__init__.py

+3 −6
Original line number Diff line number Diff line
@@ -98,9 +98,6 @@ class TensorflowGraph(object): 
      self.placeholder_root = 'placeholders'

      with tf.name_scope(self.placeholder_root) as scope:

        self.placeholder_scope = scope

        self.valid = tf.placeholder(tf.bool,

                                    shape=[model_params["batch_size"]],

                                    name='valid')



    self.setup()

    if train:
@@ -333,7 +330,7 @@ class TensorflowGraph(object): 
    for task in xrange(self.num_tasks):

      with tf.name_scope(self.placeholder_scope):

        weights.append(tf.identity(

            tf.placeholder(tf.float32, shape=[self.model_params["batch_size"]],

            tf.placeholder(tf.float32, shape=[None],

                           name='weights_%d' % task)))

    self.weights = weights
@@ -473,7 +470,7 @@ class TensorflowClassifier(TensorflowGraph): 
      for task in xrange(self.num_tasks):

        with tf.name_scope(self.placeholder_scope):

          labels.append(tf.identity(

              tf.placeholder(tf.float32, shape=[batch_size, num_classes],

              tf.placeholder(tf.float32, shape=[None, num_classes],

                             name='labels_%d' % task)))

      self.labels = labels
@@ -527,7 +524,7 @@ class TensorflowRegressor(TensorflowGraph): 
      for task in xrange(self.num_tasks):

        with tf.name_scope(self.placeholder_scope):

          labels.append(tf.identity(

              tf.placeholder(tf.float32, shape=[batch_size],

              tf.placeholder(tf.float32, shape=[None],

                             name='labels_%d' % task)))

      self.labels = labels

deepchem/models/tensorflow_models/fcnet.py

+2 −4
Original line number Diff line number Diff line
@@ -103,8 +103,7 @@ class TensorflowMultiTaskClassifier(TensorflowClassifier): 
      with tf.name_scope(self.placeholder_scope):

        self.mol_features = tf.placeholder(

            tf.float32,

            shape=[self.model_params["batch_size"],

                   num_features],

            shape=[None, num_features],

            name='mol_features')



      layer_sizes = self.model_params["layer_sizes"]
@@ -231,8 +230,7 @@ class TensorflowMultiTaskRegressor(TensorflowRegressor): 
      with tf.name_scope(self.placeholder_scope):

        self.mol_features = tf.placeholder(

            tf.float32,

            shape=[self.model_params["batch_size"],

                   num_features],

            shape=[None, num_features],

            name='mol_features')



      layer_sizes = self.model_params["layer_sizes"]

deepchem/models/tests/test_overfit.py

+2 −1
Original line number Diff line number Diff line
@@ -546,7 +546,8 @@ class TestOverfitAPI(TestAPI): 
      #"batch_size": n_samples/8,

      #"batch_size": n_samples/16,

      #"batch_size": n_samples/32,

      "batch_size": n_samples/64,

      #"batch_size": n_samples/64,

      "batch_size": 75,

      # TODO(rbharath): Is there a bug in the padding code? Why does it fail to

      # learn for non-multiples?

      #"batch_size": 600,

CRA Git | Maintained and supported by SUSTech CRA and CCSE