Progress in removing keras deps

    return concat_mol

class MultiConvMol(object):

  """Holds information about multiple molecules, for use in feeding information into

  tensorflow or keras. Generated using the agglomerate_mols function

  """Holds information about multiple molecules, for use in feeding information

     into tensorflow. Generated using the agglomerate_mols function

  """

  def __init__(self, nodes, deg_adj_lists, deg_slice, membership, num_mols):

from deepchem.models.models import Model

from deepchem.models.sklearn_models import SklearnModel

from deepchem.models.tf_keras_models.multitask_classifier import MultitaskGraphClassifier

from deepchem.models.tf_keras_models.multitask_regressor import MultitaskGraphRegressor

from deepchem.models.tf_keras_models.support_classifier import SupportGraphClassifier

from deepchem.models.tf_new_models.multitask_classifier import MultitaskGraphClassifier

from deepchem.models.tf_new_models.multitask_regressor import MultitaskGraphRegressor

from deepchem.models.tf_new_models.support_classifier import SupportGraphClassifier

from deepchem.models.multitask import SingletaskToMultitask

from deepchem.models.tensorflow_models.fcnet import TensorflowMultiTaskRegressor

__copyright__ = "Copyright 2016, Stanford University"

__license__ = "GPL"

from deepchem.models.tf_keras_models.keras_layers import GraphGather

from deepchem.models.tf_keras_models.graph_topology import GraphTopology

from deepchem.nn.layers import GraphGather

from deepchem.models.tf_new_models.graph_topology import GraphTopology

class SequentialGraph(object):

  """An analog of Keras Sequential class for Graph data.

  Like the Sequential class from Keras, but automatically passes topology

  placeholders from GraphTopology to each graph layer (from keras_layers) added

  placeholders from GraphTopology to each graph layer (from layers) added

  to the network. Non graph layers don't get the extra placeholders. 

  """

  def __init__(self, n_feat):

__copyright__ = "Copyright 2016, Stanford University"

__license__ = "GPL"

from keras.layers import Input

from keras import backend as K

from deepchem.nn.copy import Input

from deepchem.feat.mol_graphs import ConvMol

def merge_two_dicts(x, y):

"""

Implements a multitask classifier.

"""

from __future__ import print_function

from __future__ import division

from __future__ import unicode_literals

__author__ = "Han Altae-Tran and Bharath Ramsundar"

__copyright__ = "Copyright 2016, Stanford University"

__license__ = "GPL"

import os

import sys

import numpy as np

import tensorflow as tf

import sklearn.metrics

import tempfile

from keras.engine import Layer

from keras.layers import Input, Dense

from keras import initializations, activations

from keras import backend as K

from deepchem.data import pad_features

from deepchem.utils.save import log

from deepchem.models import Model 

from deepchem.nn.copy import Input

from deepchem.nn.copy import Dense

from deepchem.models.tensorflow_models import model_ops

# TODO(rbharath): Find a way to get rid of this import?

from deepchem.models.tf_keras_models.graph_topology import merge_dicts

from deepchem.models.tf_new_models.graph_topology import merge_dicts

def get_loss_fn(final_loss):

  # Obtain appropriate loss function

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

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

    # Create final dense layer from keras 

    feat = self.model.return_outputs()

    output = model_ops.multitask_logits(

        feat, self.n_tasks)

    # Get other optimizer information

    # TODO(rbharath): Figure out how to handle phase appropriately

    #keras_dict = {K.learning_phase() : training}

    keras_dict = {}

    feed_dict = merge_dicts([targets_dict, atoms_dict,

                             keras_dict])

    # old_dict = {K.learning_phase() : training}

    feed_dict = merge_dicts([targets_dict, atoms_dict ])

    return feed_dict

  def add_training_loss(self, final_loss, logits):