Commit 4bbcb551 authored by miaecle's avatar miaecle
Browse files

gdb7 modification

parent 395dc67e

examples/gdb7/gdb7_datasets.py

+1 −1
Original line number Diff line number Diff line
@@ -19,7 +19,7 @@ def load_gdb7(featurizer=None, split='random'): 
      current_dir, "./gdb7.sdf")

  gdb7_tasks = ["u0_atom"]

  if featurizer is None:

    featurizer = dc.feat.CoulombMatrixEig(23)

    featurizer = dc.feat.CoulombMatrix(23)

  else:

    raise ValueError('Only support Coulomb Matrix featurizer')

  loader = dc.data.SDFLoader(tasks=gdb7_tasks, smiles_field="smiles",

examples/gdb7/gdb7_sklearn.py

+1 −1
Original line number Diff line number Diff line
@@ -50,7 +50,7 @@ def model_builder(model_dir): 
model = dc.models.SingletaskToMultitask(tasks, model_builder, model_dir)



# Fit trained model

model.fit(train_dataset)

model.fit(train_dataset, nb_epoch=30)

model.save()



train_evaluator = dc.utils.evaluate.Evaluator(model, train_dataset, transformers)

examples/gdb7/gdb7_tf2.py

+3 −3
Original line number Diff line number Diff line
@@ -18,14 +18,14 @@ train_dataset, valid_dataset, test_dataset = datasets 
regression_metric = dc.metrics.Metric(dc.metrics.mean_absolute_error, 

                                      mode="regression")

model = dc.models.TensorflowMultiTaskRegressor(

    n_tasks=len(gdb7_tasks), n_features=23,

    learning_rate=.001, momentum=.8, batch_size=512,

    n_tasks=len(gdb7_tasks), n_features=276,

    learning_rate=.0001, momentum=.8, batch_size=512,

    weight_init_stddevs=[1/np.sqrt(2000),1/np.sqrt(800),1/np.sqrt(800),1/np.sqrt(1000)],

    bias_init_consts=[0.,0.,0.,0.], layer_sizes=[2000,800,800,1000], 

    dropouts=[0.1,0.1,0.1,0.1], seed=123)



# Fit trained model

model.fit(train_dataset)

model.fit(train_dataset, nb_epoch=50)

model.save()



train_scores = model.evaluate(train_dataset, [regression_metric], transformers)

CRA Git | Maintained and supported by SUSTech CRA and CCSE