Merge 98ad20e into 2b792b4

deepchem/models/layers.py

@@ -2344,7 +2344,13 @@ def build(self, input_shape):
     input_shape: tuple
       Ignored since we don't need the input shape to create internal weights.
     """
-    init = initializers.get(self.init)  # Set weight initialization
+
+    def init(input_shape):
+      return self.add_weight(
+          name='kernel',
+          shape=(input_shape[0], input_shape[1]),
+          initializer=self.init,
+          trainable=True)
 
     self.W_AA = init([self.n_atom_input_feat, self.n_hidden_AA])
     self.b_AA = backend.zeros(shape=[
@@ -2566,7 +2572,14 @@ def get_config(self):
 
   def build(self, input_shape):
     if self.compress_post_gaussian_expansion:
-      init = initializers.get(self.init)
+
+      def init(input_shape):
+        return self.add_weight(
+            name='kernel',
+            shape=(input_shape[0], input_shape[1]),
+            initializer=self.init,
+            trainable=True)
+
       self.W = init([self.n_input * 11, self.n_input])
       self.b = backend.zeros(shape=[self.n_input])
     self.built = True

deepchem/models/tests/test_reload.py

@@ -522,139 +522,70 @@ def test_progressivemultitaskregressor_reload():
   assert scores[regression_metric.name] < 0.1
 
 
-## TODO: THIS IS FAILING!
-#def test_DAG_regression_reload():
-#  """Test DAG regressor reloads."""
-#  np.random.seed(123)
-#  tf.random.set_seed(123)
-#  n_tasks = 1
-#  #current_dir = os.path.dirname(os.path.abspath(__file__))
-#
-#  # Load mini log-solubility dataset.
-#  featurizer = dc.feat.ConvMolFeaturizer()
-#  tasks = ["outcome"]
-#  mols = ["C", "CO", "CC"]
-#  n_samples = len(mols)
-#  X = featurizer(mols)
-#  y = np.random.rand(n_samples, n_tasks)
-#  dataset = dc.data.NumpyDataset(X, y)
-#
-#  regression_metric = dc.metrics.Metric(
-#      dc.metrics.pearson_r2_score, task_averager=np.mean)
-#
-#  n_feat = 75
-#  batch_size = 10
-#  transformer = dc.trans.DAGTransformer(max_atoms=50)
-#  dataset = transformer.transform(dataset)
-#
-#  model_dir = tempfile.mkdtemp()
-#  model = dc.models.DAGModel(
-#      n_tasks,
-#      max_atoms=50,
-#      n_atom_feat=n_feat,
-#      batch_size=batch_size,
-#      learning_rate=0.001,
-#      use_queue=False,
-#      mode="regression",
-#      model_dir=model_dir)
-#
-#  # Fit trained model
-#  model.fit(dataset, nb_epoch=1200)
-#
-#  # Eval model on train
-#  scores = model.evaluate(dataset, [regression_metric])
-#  assert scores[regression_metric.name] > .8
-#
-#  reloaded_model = dc.models.DAGModel(
-#      n_tasks,
-#      max_atoms=50,
-#      n_atom_feat=n_feat,
-#      batch_size=batch_size,
-#      learning_rate=0.001,
-#      use_queue=False,
-#      mode="regression",
-#      model_dir=model_dir)
-#  reloaded_model.restore()
-#
-#  # Check predictions match on random sample
-#  predmols = ["CCCC", "CCCCCO", "CCCCC"]
-#  Xpred = featurizer(predmols)
-#  predset = dc.data.NumpyDataset(Xpred)
-#  predset = transformer.transform(predset)
-#  origpred = model.predict(predset)
-#  reloadpred = reloaded_model.predict(predset)
-#  assert np.all(origpred == reloadpred)
-#
-#  # Eval model on train
-#  scores = reloaded_model.evaluate(dataset, [classification_metric])
-#  assert scores[classification_metric.name] > .9
+def test_weave_classification_reload():
+  """Test weave model can be reloaded."""
+  np.random.seed(123)
+  tf.random.set_seed(123)
+  n_tasks = 1
+
+  # Load mini log-solubility dataset.
+  featurizer = dc.feat.WeaveFeaturizer()
+  tasks = ["outcome"]
+  mols = ["CC", "CCCCC", "CCCCC", "CCC", "COOO", "COO", "OO"]
+  n_samples = len(mols)
+  X = featurizer(mols)
+  y = [1, 1, 1, 1, 0, 0, 0]
+  dataset = dc.data.NumpyDataset(X, y)
+
+  classification_metric = dc.metrics.Metric(dc.metrics.roc_auc_score)
+
+  batch_size = 5
+
+  model_dir = tempfile.mkdtemp()
+  model = dc.models.WeaveModel(
+      n_tasks,
+      batch_size=batch_size,
+      learning_rate=0.01,
+      mode="classification",
+      dropouts=0.0,
+      model_dir=model_dir)
+
+  # Fit trained model
+  model.fit(dataset, nb_epoch=100)
+
+  # Eval model on train
+  scores = model.evaluate(dataset, [classification_metric])
+  assert scores[classification_metric.name] > .6
+
+  # Check predictions match on random sample
+  predmols = ["CCCC", "CCCCCO", "CCCCC"]
+  Xpred = featurizer(predmols)
+
+  predset = dc.data.NumpyDataset(Xpred)
+  origpred = model.predict(predset)
+
+  reloaded_model = dc.models.WeaveModel(
+      n_tasks,
+      batch_size=batch_size,
+      learning_rate=0.003,
+      mode="classification",
+      dropouts=0.0,
+      model_dir=model_dir)
+  reloaded_model.restore()
+
+  # Check predictions match on random sample
+  predmols = ["CCCC", "CCCCCO", "CCCCC"]
+  Xpred = featurizer(predmols)
+  predset = dc.data.NumpyDataset(Xpred)
+  origpred = model.predict(predset)
+  reloadpred = reloaded_model.predict(predset)
+  assert np.all(origpred == reloadpred)
+
+  #Eval model on train
+  scores = reloaded_model.evaluate(dataset, [classification_metric])
+  assert scores[classification_metric.name] > .6
+
 
-## TODO: THIS IS FAILING!
-#def test_weave_classification_reload_alt():
-#  """Test weave model can be reloaded."""
-#  np.random.seed(123)
-#  tf.random.set_seed(123)
-#  n_tasks = 1
-#
-#  # Load mini log-solubility dataset.
-#  featurizer = dc.feat.WeaveFeaturizer()
-#  tasks = ["outcome"]
-#  mols = ["C", "CO", "CC"]
-#  n_samples = len(mols)
-#  X = featurizer(mols)
-#  y = np.random.randint(2, size=(n_samples, n_tasks))
-#  dataset = dc.data.NumpyDataset(X, y)
-#
-#  classification_metric = dc.metrics.Metric(dc.metrics.roc_auc_score)
-#
-#  batch_size = 10
-#
-#  model_dir = tempfile.mkdtemp()
-#  model = dc.models.WeaveModel(
-#      n_tasks,
-#      batch_size=batch_size,
-#      learning_rate=0.0003,
-#      mode="classification",
-#      dropouts=0.0,
-#      model_dir=model_dir)
-#
-#  # Fit trained model
-#  model.fit(dataset, nb_epoch=30)
-#
-#  # Eval model on train
-#  scores = model.evaluate(dataset, [classification_metric])
-#  assert scores[classification_metric.name] > .9
-#
-#  # Custom save
-#  save_dir = tempfile.mkdtemp()
-#  model.model.save(save_dir)
-#
-#  from tensorflow import keras
-#  reloaded = keras.models.load_model(save_dir)
-#
-#  reloaded_model = dc.models.WeaveModel(
-#      n_tasks,
-#      batch_size=batch_size,
-#      learning_rate=0.0003,
-#      mode="classification",
-#      dropouts=0.0,
-#      model_dir=model_dir)
-#  #reloaded_model.restore()
-#  reloaded_model.model = reloaded
-#
-#  # Check predictions match on random sample
-#  predmols = ["CCCC", "CCCCCO", "CCCCC"]
-#  Xpred = featurizer(predmols)
-#  predset = dc.data.NumpyDataset(Xpred)
-#  origpred = model.predict(predset)
-#  reloadpred = reloaded_model.predict(predset)
-#  assert np.all(origpred == reloadpred)
-#
-#  # Eval model on train
-#  scores = reloaded_model.evaluate(dataset, [classification_metric])
-#  assert scores[classification_metric.name] > .9
-#
-#
 ## TODO: THIS IS FAILING!
 #@pytest.mark.slow
 #def test_weave_classification_reload():