Commit 2609b33f authored by peastman's avatar peastman
Browse files

Merge branch 'master' into seq2seq

parents ec2a06d0 7dec6843

deepchem/models/tensorgraph/layers.py

+35 −2
Original line number Diff line number Diff line
@@ -162,6 +162,39 @@ class Layer(object): 
    else:

      return self.out_tensor



  def __add__(self, other):

    if not isinstance(other, Layer):

      other = Constant(other)

    return Add([self, other])



  def __radd__(self, other):

    if not isinstance(other, Layer):

      other = Constant(other)

    return Add([other, self])



  def __sub__(self, other):

    if not isinstance(other, Layer):

      other = Constant(other)

    return Add([self, other], weights=[1.0, -1.0])



  def __rsub__(self, other):

    if not isinstance(other, Layer):

      other = Constant(other)

    return Add([other, self], weights=[1.0, -1.0])



  def __mul__(self, other):

    if not isinstance(other, Layer):

      other = Constant(other)

    return Multiply([self, other])



  def __rmul__(self, other):

    if not isinstance(other, Layer):

      other = Constant(other)

    return Multiply([other, self])



  def __neg__(self):

    return Multiply([self, Constant(-1.0)])





def _convert_layer_to_tensor(value, dtype=None, name=None, as_ref=False):

  return tf.convert_to_tensor(value.out_tensor, dtype=dtype, name=name)
@@ -1302,7 +1335,7 @@ class Conv3D(Layer): 
    return out_tensor





class MaxPool(Layer):

class MaxPool2D(Layer):



  def __init__(self,

               ksize=[1, 2, 2, 1],
@@ -1312,7 +1345,7 @@ class MaxPool(Layer): 
    self.ksize = ksize

    self.strides = strides

    self.padding = padding

    super(MaxPool, self).__init__(**kwargs)

    super(MaxPool2D, self).__init__(**kwargs)

    try:

      parent_shape = self.in_layers[0].shape

      self._shape = tuple(None if p is None else p // s

deepchem/models/tensorgraph/symmetry_functions.py

+30 −21
Original line number Diff line number Diff line
@@ -403,8 +403,8 @@ class AtomicDifferentiatedDense(Layer): 
               init='glorot_uniform',

               activation='relu',

               **kwargs):

    self.init = initializations.get(init)  # Set weight initialization

    self.activation = activations.get(activation)  # Get activations

    self.init = init  # Set weight initialization

    self.activation = activation  # Get activations

    self.max_atoms = max_atoms

    self.out_channels = out_channels

    self.atom_number_cases = atom_number_cases
@@ -413,6 +413,8 @@ class AtomicDifferentiatedDense(Layer): 


  def create_tensor(self, in_layers=None, set_tensors=True, **kwargs):

    """ Generate Radial Symmetry Function """

    init_fn = initializations.get(self.init)  # Set weight initialization

    activation_fn = activations.get(self.activation)

    if in_layers is None:

      in_layers = self.in_layers

    in_layers = convert_to_layers(in_layers)
@@ -420,13 +422,12 @@ class AtomicDifferentiatedDense(Layer): 
    inputs = in_layers[0].out_tensor

    atom_numbers = in_layers[1].out_tensor

    in_channels = inputs.get_shape().as_list()[-1]

    self.W = self.init(

    self.W = init_fn(

        [len(self.atom_number_cases), in_channels, self.out_channels])



    self.b = model_ops.zeros((len(self.atom_number_cases), self.out_channels))

    outputs = []

    for i, atom_case in enumerate(self.atom_number_cases):



      # optimization to allow for tensorcontraction/broadcasted mmul

      # using a reshape trick. Note that the np and tf matmul behavior

      # differs when dealing with broadcasts
@@ -439,7 +440,7 @@ class AtomicDifferentiatedDense(Layer): 
      ak = tf.shape(a)[2]

      bl = tf.shape(b)[1]



      output = self.activation(

      output = activation_fn(

          tf.reshape(tf.matmul(tf.reshape(a, [ai * aj, ak]), b), [ai, aj, bl]) +

          self.b[i, :])
@@ -448,3 +449,11 @@ class AtomicDifferentiatedDense(Layer): 
                                                             self.out_channels))

      outputs.append(output)

    self.out_tensor = tf.add_n(outputs)



  def none_tensors(self):

    w, b, out_tensor = self.W, self.b, self.out_tensor

    self.W, self.b, self.out_tensor = None, None, None

    return w, b, out_tensor



  def set_tensors(self, tensor):

    self.W, self.b, self.out_tensor = tensor

deepchem/models/tensorgraph/tensor_graph.py

+6 −7
Original line number Diff line number Diff line
@@ -291,16 +291,15 @@ class TensorGraph(Model): 
    elif not isinstance(outputs, collections.Sequence):

      outputs = [outputs]

    with self._get_tf("Graph").as_default():

      out_tensors = [x.out_tensor for x in self.outputs]

      # Gather results for each output

      results = [[] for out in out_tensors]

      results = [[] for out in outputs]

      for feed_dict in generator:

        feed_dict = {

            self.layers[k.name].out_tensor: v

            for k, v in six.iteritems(feed_dict)

        }

        feed_dict[self._training_placeholder] = 0.0

        feed_results = self.session.run(out_tensors, feed_dict=feed_dict)

        feed_results = self.session.run(outputs, feed_dict=feed_dict)

        if len(feed_results) > 1:

          if len(transformers):

            raise ValueError("Does not support transformations "
@@ -328,7 +327,7 @@ class TensorGraph(Model): 
    """

    return self.predict_on_generator(generator, transformers, outputs)



  def predict_on_batch(self, X, transformers=[]):

  def predict_on_batch(self, X, transformers=[], outputs=None):

    """Generates predictions for input samples, processing samples in a batch.



    Parameters
@@ -344,9 +343,9 @@ class TensorGraph(Model): 
    """

    dataset = NumpyDataset(X=X, y=None)

    generator = self.default_generator(dataset, predict=True, pad_batches=False)

    return self.predict_on_generator(generator, transformers)

    return self.predict_on_generator(generator, transformers, outputs)



  def predict_proba_on_batch(self, X, transformers=[]):

  def predict_proba_on_batch(self, X, transformers=[], outputs=None):

    """Generates predictions for input samples, processing samples in a batch.



    Parameters
@@ -360,7 +359,7 @@ class TensorGraph(Model): 
    -------

    A Numpy array of predictions.

    """

    return self.predict_on_batch(X, transformers)

    return self.predict_on_batch(X, transformers, outputs)



  def predict(self, dataset, transformers=[], outputs=None):

    """

deepchem/models/tensorgraph/tests/test_layers.py

+34 −44
Original line number Diff line number Diff line 
import unittest



import numpy as np

import os

import rdkit

import tensorflow as tf

from nose.tools import assert_true

from tensorflow.python.framework import test_util

from deepchem.feat.mol_graphs import ConvMol

from deepchem.feat.mol_graphs import MultiConvMol



from deepchem.feat.graph_features import ConvMolFeaturizer

from deepchem.feat.mol_graphs import ConvMol

from deepchem.models.tensorgraph.layers import Add, Conv3D, MaxPool2D, MaxPool3D

from deepchem.models.tensorgraph.layers import AlphaShareLayer

from deepchem.models.tensorgraph.layers import AttnLSTMEmbedding

from deepchem.models.tensorgraph.layers import BatchNorm

from deepchem.models.tensorgraph.layers import BetaShare

from deepchem.models.tensorgraph.layers import CombineMeanStd

from deepchem.models.tensorgraph.layers import Concat

from deepchem.models.tensorgraph.layers import Constant

from deepchem.models.tensorgraph.layers import Conv1D, Squeeze

from deepchem.models.tensorgraph.layers import Conv2D

from deepchem.models.tensorgraph.layers import Dense

from deepchem.models.tensorgraph.layers import Flatten

from deepchem.models.tensorgraph.layers import Reshape

from deepchem.models.tensorgraph.layers import Transpose

from deepchem.models.tensorgraph.layers import CombineMeanStd

from deepchem.models.tensorgraph.layers import Repeat

from deepchem.models.tensorgraph.layers import Gather

from deepchem.models.tensorgraph.layers import GRU

from deepchem.models.tensorgraph.layers import TimeSeriesDense

from deepchem.models.tensorgraph.layers import Gather

from deepchem.models.tensorgraph.layers import GraphConv

from deepchem.models.tensorgraph.layers import GraphGather

from deepchem.models.tensorgraph.layers import Input

from deepchem.models.tensorgraph.layers import InputFifoQueue

from deepchem.models.tensorgraph.layers import InteratomicL2Distances

from deepchem.models.tensorgraph.layers import IterRefLSTMEmbedding

from deepchem.models.tensorgraph.layers import L2Loss

from deepchem.models.tensorgraph.layers import Concat

from deepchem.models.tensorgraph.layers import Constant

from deepchem.models.tensorgraph.layers import Variable

from deepchem.models.tensorgraph.layers import Add

from deepchem.models.tensorgraph.layers import Multiply

from deepchem.models.tensorgraph.layers import LSTMStep

from deepchem.models.tensorgraph.layers import LayerSplitter

from deepchem.models.tensorgraph.layers import Log

from deepchem.models.tensorgraph.layers import InteratomicL2Distances

from deepchem.models.tensorgraph.layers import SoftMaxCrossEntropy

from deepchem.models.tensorgraph.layers import Multiply

from deepchem.models.tensorgraph.layers import ReduceMean

from deepchem.models.tensorgraph.layers import ToFloat

from deepchem.models.tensorgraph.layers import ReduceSum

from deepchem.models.tensorgraph.layers import ReduceSquareDifference

from deepchem.models.tensorgraph.layers import Conv2D

from deepchem.models.tensorgraph.layers import Conv3D

from deepchem.models.tensorgraph.layers import MaxPool

from deepchem.models.tensorgraph.layers import MaxPool3D

from deepchem.models.tensorgraph.layers import InputFifoQueue

from deepchem.models.tensorgraph.layers import GraphConv

from deepchem.models.tensorgraph.layers import GraphPool

from deepchem.models.tensorgraph.layers import GraphGather

from deepchem.models.tensorgraph.layers import BatchNorm

from deepchem.models.tensorgraph.layers import ReduceSum

from deepchem.models.tensorgraph.layers import Repeat

from deepchem.models.tensorgraph.layers import Reshape

from deepchem.models.tensorgraph.layers import SluiceLoss

from deepchem.models.tensorgraph.layers import SoftMax

from deepchem.models.tensorgraph.layers import WeightedError

from deepchem.models.tensorgraph.layers import SoftMaxCrossEntropy

from deepchem.models.tensorgraph.layers import TensorWrapper

from deepchem.models.tensorgraph.layers import TimeSeriesDense

from deepchem.models.tensorgraph.layers import ToFloat

from deepchem.models.tensorgraph.layers import Transpose

from deepchem.models.tensorgraph.layers import Variable

from deepchem.models.tensorgraph.layers import VinaFreeEnergy

from deepchem.models.tensorgraph.layers import WeightedError

from deepchem.models.tensorgraph.layers import WeightedLinearCombo

from deepchem.models.tensorgraph.layers import TensorWrapper

from deepchem.models.tensorgraph.layers import LSTMStep

from deepchem.models.tensorgraph.layers import AttnLSTMEmbedding

from deepchem.models.tensorgraph.layers import IterRefLSTMEmbedding

from deepchem.models.tensorgraph.layers import AlphaShareLayer

from deepchem.models.tensorgraph.layers import BetaShare

from deepchem.models.tensorgraph.layers import LayerSplitter

from deepchem.models.tensorgraph.layers import SluiceLoss



import deepchem as dc





class TestLayers(test_util.TensorFlowTestCase):
@@ -387,8 +377,8 @@ class TestLayers(test_util.TensorFlowTestCase): 
      assert out_tensor.shape == (batch_size, length, width, depth,

                                  out_channels)



  def test_max_pool(self):

    """Test that MaxPool can be invoked."""

  def test_maxpool2D(self):

    """Test that MaxPool2D can be invoked."""

    length = 2

    width = 2

    in_channels = 2
@@ -396,7 +386,7 @@ class TestLayers(test_util.TensorFlowTestCase): 
    in_tensor = np.random.rand(batch_size, length, width, in_channels)

    with self.test_session() as sess:

      in_tensor = tf.convert_to_tensor(in_tensor, dtype=tf.float32)

      out_tensor = MaxPool()(in_tensor)

      out_tensor = MaxPool2D()(in_tensor)

      sess.run(tf.global_variables_initializer())

      out_tensor = out_tensor.eval()

      assert out_tensor.shape == (batch_size, 1, 1, in_channels)

deepchem/models/tensorgraph/tests/test_layers_pickle.py

+27 −10
Original line number Diff line number Diff line 
import numpy as np

import tensorflow as tf



from deepchem.models import TensorGraph

from deepchem.models.tensorgraph.graph_layers import Combine_AP, Separate_AP, \

  WeaveLayer, WeaveGather, DTNNEmbedding, DTNNGather, DTNNStep, \

  DTNNExtract, DAGLayer, DAGGather, MessagePassing, SetGather

from deepchem.models.tensorgraph.layers import Feature, Conv1D, Dense, Flatten, Reshape, Squeeze, Transpose, \

    CombineMeanStd, Repeat, Gather, GRU, L2Loss, Concat, SoftMax, Constant, Variable, Add, Multiply, Log, InteratomicL2Distances, \

    SoftMaxCrossEntropy, ReduceMean, ToFloat, ReduceSquareDifference, Conv2D, MaxPool, ReduceSum, GraphConv, GraphPool, \

  CombineMeanStd, Repeat, Gather, GRU, L2Loss, Concat, SoftMax, \

  Constant, Variable, Add, Multiply, Log, InteratomicL2Distances, \

  SoftMaxCrossEntropy, ReduceMean, ToFloat, ReduceSquareDifference, Conv2D, MaxPool2D, ReduceSum, GraphConv, GraphPool, \

  GraphGather, BatchNorm, WeightedError, \

  Conv3D, MaxPool3D, \

  LSTMStep, AttnLSTMEmbedding, IterRefLSTMEmbedding

from deepchem.models.tensorgraph.graph_layers import Combine_AP, Separate_AP, \

    WeaveLayer, WeaveGather, DTNNEmbedding, DTNNGather, DTNNStep, \

    DTNNExtract, DAGLayer, DAGGather, MessagePassing, SetGather

from deepchem.models.tensorgraph.symmetry_functions import AtomicDifferentiatedDense





def test_Conv1D_pickle():
@@ -266,10 +269,10 @@ def test_Conv3D_pickle(): 
  tg.save()





def test_MaxPool_pickle():

def test_MaxPool2D_pickle():

  tg = TensorGraph()

  feature = Feature(shape=(tg.batch_size, 10, 10, 10))

  layer = MaxPool(in_layers=feature)

  layer = MaxPool2D(in_layers=feature)

  tg.add_output(layer)

  tg.set_loss(layer)

  tg.build()
@@ -541,3 +544,17 @@ def test_SetGather_pickle(): 
  tg.set_loss(Gather)

  tg.build()

  tg.save()





def test_AtomicDifferentialDense_pickle():

  max_atoms = 23

  atom_features = 100

  tg = TensorGraph()

  atom_feature = Feature(shape=(None, max_atoms, atom_features))

  atom_numbers = Feature(shape=(None, max_atoms))

  atomic_differential_dense = AtomicDifferentiatedDense(

      max_atoms=23, out_channels=5, in_layers=[atom_feature, atom_numbers])

  tg.add_output(atomic_differential_dense)

  tg.set_loss(atomic_differential_dense)

  tg.build()

  tg.save()

CRA Git | Maintained and supported by SUSTech CRA and CCSE