Commit 005942c3 authored by miaecle's avatar miaecle
Browse files

add masking

parent 00942093

deepchem/models/tf_new_models/DTNN_regressor.py

deleted100644 → 0
+0 −82
Original line number Diff line number Diff line 
#!/usr/bin/env python2

# -*- coding: utf-8 -*-

"""

Created on Mon Mar 13 14:42:40 2017



@author: zqwu

"""

import os

import numpy as np

import tensorflow as tf

import sklearn.metrics

import tempfile

from deepchem.models.tf_new_models.multitask_regressor import MultitaskGraphRegressor





class DTNNRegressor(MultitaskGraphRegressor):



  def __init__(self,

               model,

               n_tasks=1,

               logdir=None,

               batch_size=50,

               final_loss='weighted_L2',

               learning_rate=.001,

               optimizer_type="adam",

               learning_rate_decay_time=1000,

               beta1=.9,

               beta2=.999,

               pad_batches=True,

               verbose=True):

    self.n_tasks = n_tasks

    self.verbose = verbose

    self.n_tasks = n_tasks

    self.final_loss = final_loss

    self.model = model

    self.sess = tf.Session(graph=self.model.graph)

    if logdir is not None:

      if not os.path.exists(logdir):

        os.makedirs(logdir)

    else:

      logdir = tempfile.mkdtemp()

    self.logdir = logdir



    with self.model.graph.as_default():

      # Extract model info 

      self.batch_size = batch_size

      self.pad_batches = pad_batches

      # Get graph topology for x

      self.graph_topology = self.model.get_graph_topology()



      # Building outputs

      self.outputs = self.build()

      self.loss_op = self.add_training_loss(self.final_loss, self.outputs)



      self.learning_rate = learning_rate

      self.T = learning_rate_decay_time

      self.optimizer_type = optimizer_type



      self.optimizer_beta1 = beta1

      self.optimizer_beta2 = beta2



      # Set epsilon

      self.epsilon = 1e-7

      self.add_optimizer()



      # Initialize

      self.init_fn = tf.global_variables_initializer()

      self.sess.run(self.init_fn)



      # Path to save checkpoint files, which matches the

      # replicated supervisor's default path.

      self._save_path = os.path.join(logdir, 'model.ckpt')



  def build(self):

    # Create target inputs

    self.label_placeholder = tf.placeholder(

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

    self.weight_placeholder = tf.placeholder(

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



    outputs = self.model.return_outputs()

    return outputs

deepchem/models/tf_new_models/graph_models.py

+3 −3
Original line number Diff line number Diff line
@@ -121,6 +121,9 @@ class SequentialDTNNGraph(SequentialGraph): 
      if type(layer).__name__ in ['DTNNStep']:

        self.output = layer([self.output] +

                            self.graph_topology.get_topology_placeholders())

      elif type(layer).__name__ in ['DTNNGather']:

        self.output = layer(

            [self.output, self.graph_topology.atom_mask_placeholder])

      else:

        self.output = layer(self.output)

      self.layers.append(layer)
@@ -128,9 +131,6 @@ class SequentialDTNNGraph(SequentialGraph): 
  def return_inputs(self):

    return self.graph_topology.get_atom_number_placeholders()



  def get_layer(self, layer_id):

    return self.layers[layer_id]





class SequentialSupportGraph(object):

  """An analog of Keras Sequential model for test/support models."""

deepchem/models/tf_new_models/graph_topology.py

+7 −1
Original line number Diff line number Diff line
@@ -176,12 +176,16 @@ class DTNNGraphTopology(GraphTopology): 
        dtype='int32',

        shape=(None, self.max_n_atoms),

        name=self.name + '_atom_number')

    self.atom_mask_placeholder = tf.placeholder(

        dtype='float32',

        shape=(None, self.max_n_atoms),

        name=self.name + '_atom_mask')

    self.distance_matrix_placeholder = tf.placeholder(

        dtype='float32',

        shape=(None, self.max_n_atoms, self.max_n_atoms, self.n_distance),

        name=self.name + '_distance_matrix')

    self.distance_matrix_mask_placeholder = tf.placeholder(

        dtype=tf.float32,

        dtype='float32',

        shape=(None, self.max_n_atoms, self.max_n_atoms),

        name=self.name + '_distance_matrix_mask')
@@ -216,6 +220,7 @@ class DTNNGraphTopology(GraphTopology): 
    """

    # Extract atom numbers

    atom_number = np.asarray(map(np.diag, batch))

    atom_mask = np.sign(atom_number)

    atom_number = np.asarray(

        np.round(np.power(2 * atom_number, 1 / 2.4)), dtype=int)

    ZiZj = []
@@ -241,6 +246,7 @@ class DTNNGraphTopology(GraphTopology): 
    # Generate dicts

    dict_DTNN = {

        self.atom_number_placeholder: atom_number,

        self.atom_mask_placeholder: atom_mask,

        self.distance_matrix_placeholder: distance_matrix,

        self.distance_matrix_mask_placeholder: distance_matrix_mask

    }

deepchem/molnet/preset_hyper_parameters.py

+0 −9
Original line number Diff line number Diff line
@@ -91,12 +91,3 @@ hps['graphconvreg'] = { 
    'n_fully_connected_nodes': 256,

    'seed': 123

}
 
hps['DTNN'] = {

    'batch_size': 128,

    'nb_epoch': 20,

    'learning_rate': 0.0005,

    'n_embedding': 20,

    'n_hidden': 50,

    'n_distance': 100,

    'seed': 123

}

deepchem/molnet/run_benchmark_models.py

+3 −36
Original line number Diff line number Diff line
@@ -303,8 +303,7 @@ def benchmark_regression( 
  test_scores = {}



  assert model in [

      'tf_regression', 'tf_regression_ft', 'rf_regression', 'graphconvreg',

      'DTNN'

      'tf_regression', 'tf_regression_ft', 'rf_regression', 'graphconvreg'

  ]

  if hyper_parameters is None:

    hyper_parameters = hps[model]
@@ -364,7 +363,7 @@ def benchmark_regression( 
        n_eval=10,

        seed=seed)



  elif model_name == 'graphconvreg':

  if model_name == 'graphconvreg':

    # Initialize model folder



    # Loading hyper parameters
@@ -401,39 +400,7 @@ def benchmark_regression( 
        beta1=.9,

        beta2=.999)



  elif model_name == 'DTNN':

    # Initialize model folder



    # Loading hyper parameters

    batch_size = hyper_parameters['batch_size']

    nb_epoch = hyper_parameters['nb_epoch']

    learning_rate = hyper_parameters['learning_rate']

    n_distance = hyper_parameters['n_distance']

    n_embedding = hyper_parameters['n_embedding']

    n_hidden = hyper_parameters['n_hidden']



    tf.set_random_seed(seed)

    graph_model = deepchem.nn.SequentialDTNNGraph(

        max_n_atoms=n_features[0], n_distance=n_distance)

    graph_model.add(deepchem.nn.DTNNEmbedding(n_embedding=n_embedding))

    graph_model.add(

        deepchem.nn.DTNNStep(n_embedding=n_embedding, n_distance=n_distance))

    graph_model.add(

        deepchem.nn.DTNNStep(n_embedding=n_embedding, n_distance=n_distance))

    graph_model.add(

        deepchem.nn.DTNNGather(

            n_tasks=len(tasks), n_embedding=n_embedding, n_hidden=n_hidden))



    model = deepchem.models.DTNNRegressor(

        graph_model,

        n_tasks=len(tasks),

        batch_size=batch_size,

        learning_rate=learning_rate,

        optimizer_type="adam",

        beta1=.9,

        beta2=.999)



  elif model_name == 'rf_regression':

  if model_name == 'rf_regression':

    # Loading hyper parameters

    n_estimators = hyper_parameters['n_estimators']

    nb_epoch = None

CRA Git | Maintained and supported by SUSTech CRA and CCSE