Commit cff6617e authored by Bharath Ramsundar's avatar Bharath Ramsundar
Browse files

YAPF

parent 9d7d558b

examples/low_data/muv_attn_one_fold.py

+18 −12
Original line number Diff line number Diff line
@@ -55,11 +55,13 @@ support_model.add(dc.nn.GraphPool()) 
support_model.add(dc.nn.Dense(128, 64, activation='tanh'))



support_model.add_test(dc.nn.GraphGather(test_batch_size, activation='tanh'))

support_model.add_support(dc.nn.GraphGather(support_batch_size, activation='tanh'))

support_model.add_support(

    dc.nn.GraphGather(support_batch_size, activation='tanh'))



# Apply an attention lstm layer

support_model.join(dc.nn.AttnLSTMEmbedding(

    test_batch_size, support_batch_size, 128, max_depth))

support_model.join(

    dc.nn.AttnLSTMEmbedding(test_batch_size, support_batch_size, 128,

                            max_depth))



model = dc.models.SupportGraphClassifier(

    support_model,
@@ -67,9 +69,13 @@ model = dc.models.SupportGraphClassifier( 
    support_batch_size=support_batch_size,

    learning_rate=learning_rate)



model.fit(train_dataset, nb_epochs=nb_epochs, 

model.fit(

    train_dataset,

    nb_epochs=nb_epochs,

    n_episodes_per_epoch=n_train_trials,

          n_pos=n_pos, n_neg=n_neg, log_every_n_samples=log_every_n_samples)

    n_pos=n_pos,

    n_neg=n_neg,

    log_every_n_samples=log_every_n_samples)

mean_scores, std_scores = model.evaluate(

    test_dataset, metric, n_pos, n_neg, n_trials=n_eval_trials)

examples/low_data/muv_graph_conv_one_fold.py

+15 −16
Original line number Diff line number Diff line
@@ -32,8 +32,8 @@ train_dataset = dc.splits.merge_fold_datasets(train_folds) 
test_dataset = fold_datasets[-1]



# Get supports on test-set

support_generator = dc.data.SupportGenerator(

    test_dataset, n_pos, n_neg, n_trials)

support_generator = dc.data.SupportGenerator(test_dataset, n_pos, n_neg,

                                             n_trials)



# Compute accuracies

task_scores = {task: [] for task in range(len(test_dataset.get_task_names()))}
@@ -70,11 +70,10 @@ for trial_num, (task, support) in enumerate(support_generator): 
  model.fit(support, nb_epoch=10)



  # Test model

  task_dataset = dc.data.get_task_dataset_minus_support(

      test_dataset, support, task)

  task_dataset = dc.data.get_task_dataset_minus_support(test_dataset, support,

                                                        task)

  y_pred = model.predict_proba(task_dataset)

  score = metric.compute_metric(

      task_dataset.y, y_pred, task_dataset.w)

  score = metric.compute_metric(task_dataset.y, y_pred, task_dataset.w)

  print("Score on task %s is %s" % (str(task), str(score)))

  task_scores[task].append(score)

examples/low_data/muv_res_one_fold.py

+18 −12
Original line number Diff line number Diff line
@@ -55,11 +55,13 @@ support_model.add(dc.nn.GraphPool()) 
support_model.add(dc.nn.Dense(128, 64, activation='tanh'))



support_model.add_test(dc.nn.GraphGather(test_batch_size, activation='tanh'))

support_model.add_support(dc.nn.GraphGather(support_batch_size, activation='tanh'))

support_model.add_support(

    dc.nn.GraphGather(support_batch_size, activation='tanh'))



# Apply a residual lstm layer

support_model.join(dc.nn.ResiLSTMEmbedding(

    test_batch_size, support_batch_size, 128, max_depth))

support_model.join(

    dc.nn.ResiLSTMEmbedding(test_batch_size, support_batch_size, 128,

                            max_depth))



model = dc.models.SupportGraphClassifier(

    support_model,
@@ -67,9 +69,13 @@ model = dc.models.SupportGraphClassifier( 
    support_batch_size=support_batch_size,

    learning_rate=learning_rate)



model.fit(train_dataset, nb_epochs=nb_epochs,

model.fit(

    train_dataset,

    nb_epochs=nb_epochs,

    n_episodes_per_epoch=n_train_trials,

          n_pos=n_pos, n_neg=n_neg, log_every_n_samples=log_every_n_samples)

    n_pos=n_pos,

    n_neg=n_neg,

    log_every_n_samples=log_every_n_samples)

mean_scores, std_scores = model.evaluate(

    test_dataset, metric, n_pos, n_neg, n_trials=n_eval_trials)

examples/low_data/muv_siamese_one_fold.py

+16 −11
Original line number Diff line number Diff line
@@ -52,7 +52,8 @@ support_model.add(dc.nn.GraphPool()) 
support_model.add(dc.nn.Dense(128, 64, activation='tanh'))



support_model.add_test(dc.nn.GraphGather(test_batch_size, activation='tanh'))

support_model.add_support(dc.nn.GraphGather(support_batch_size, activation='tanh'))

support_model.add_support(

    dc.nn.GraphGather(support_batch_size, activation='tanh'))



model = dc.models.SupportGraphClassifier(

    support_model,
@@ -60,9 +61,13 @@ model = dc.models.SupportGraphClassifier( 
    support_batch_size=support_batch_size,

    learning_rate=learning_rate)



model.fit(train_dataset, nb_epochs=nb_epochs,

model.fit(

    train_dataset,

    nb_epochs=nb_epochs,

    n_episodes_per_epoch=n_train_trials,

          n_pos=n_pos, n_neg=n_neg, log_every_n_samples=log_every_n_samples)

    n_pos=n_pos,

    n_neg=n_neg,

    log_every_n_samples=log_every_n_samples)

mean_scores, std_scores = model.evaluate(

    test_dataset, metric, n_pos, n_neg, n_trials=n_eval_trials)

examples/low_data/sider_attn_one_fold.py

+18 −12
Original line number Diff line number Diff line
@@ -55,11 +55,13 @@ support_model.add(dc.nn.GraphPool()) 
support_model.add(dc.nn.Dense(128, 64, activation='tanh'))



support_model.add_test(dc.nn.GraphGather(test_batch_size, activation='tanh'))

support_model.add_support(dc.nn.GraphGather(support_batch_size, activation='tanh'))

support_model.add_support(

    dc.nn.GraphGather(support_batch_size, activation='tanh'))



# Apply an attention lstm layer

support_model.join(dc.nn.AttnLSTMEmbedding(

    test_batch_size, support_batch_size, 128, max_depth))

support_model.join(

    dc.nn.AttnLSTMEmbedding(test_batch_size, support_batch_size, 128,

                            max_depth))



model = dc.models.SupportGraphClassifier(

    support_model,
@@ -67,9 +69,13 @@ model = dc.models.SupportGraphClassifier( 
    support_batch_size=support_batch_size,

    learning_rate=learning_rate)



model.fit(train_dataset, nb_epochs=nb_epochs, 

model.fit(

    train_dataset,

    nb_epochs=nb_epochs,

    n_episodes_per_epoch=n_train_trials,

          n_pos=n_pos, n_neg=n_neg, log_every_n_samples=log_every_n_samples)

    n_pos=n_pos,

    n_neg=n_neg,

    log_every_n_samples=log_every_n_samples)

mean_scores, std_scores = model.evaluate(

    test_dataset, metric, n_pos, n_neg, n_trials=n_eval_trials)

CRA Git | Maintained and supported by SUSTech CRA and CCSE