fix nas on clf, rename example

autogl/solver/classifier/node_classifier.py

@@ -826,9 +826,9 @@ class AutoNodeClassifier(BaseClassifier):
                 configs = nas_dict[k]
                 if isinstance(configs, list):
                     for item in configs:
-                        container.append(indexer[item.pop('name')](**item, init=False))
+                        container.append(indexer[item.pop('name')](**item))
                 else:
-                    container.append(indexer[configs.pop('name')](**configs, init=False))
+                    container.append(indexer[configs.pop('name')](**configs))
             
             solver.set_nas_module(algorithms, spaces, estimators)
 

configs/nodeclf_nas_benchmark.yml

@@ -0,0 +1,40 @@
+ensemble:
+  name: null
+feature:
+- name: PYGNormalizeFeatures
+hpo:
+  max_evals: 10
+  name: random
+nas:
+  space:
+    name: graphnas
+    hidden_dim: 64
+    layer_number: 4
+  algorithm:
+    name: rl
+    num_epochs: 200
+  estimator:
+    name: scratch
+models: []
+trainer:
+  hp_space:
+  - maxValue: 300
+    minValue: 100
+    parameterName: max_epoch
+    scalingType: LINEAR
+    type: INTEGER
+  - maxValue: 30
+    minValue: 10
+    parameterName: early_stopping_round
+    scalingType: LINEAR
+    type: INTEGER
+  - maxValue: 0.05
+    minValue: 0.01
+    parameterName: lr
+    scalingType: LOG
+    type: DOUBLE
+  - maxValue: 0.0005
+    minValue: 5.0e-05
+    parameterName: weight_decay
+    scalingType: LOG
+    type: DOUBLE

examples/graphnas.py

@@ -0,0 +1,20 @@
+import sys
+sys.path.append('../')
+from autogl.datasets import build_dataset_from_name
+from autogl.solver import AutoNodeClassifier
+from autogl.module.train import Acc
+import argparse
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--config', type=str, default='../configs/nodeclf_nas_benchmark.yml')
+    parser.add_argument('--dataset', choices=['cora', 'citeseer', 'pubmed'], default='cora', type=str)
+
+    args = parser.parse_args()
+
+    dataset = build_dataset_from_name('cora')
+    solver = AutoNodeClassifier.from_config(args.config)
+    solver.fit(dataset)
+    solver.get_leaderboard().show()
+    out = solver.predict_proba()
+    print('acc on cora', Acc.evaluate(out, dataset[0].y[dataset[0].test_mask].detach().numpy()))

examples/test_nas.py

@@ -1,40 +0,0 @@
-import sys
-sys.path.append('../')
-from torch_geometric.nn import GCNConv
-import torch
-from autogl.datasets import build_dataset_from_name
-from autogl.solver import AutoNodeClassifier
-from autogl.module.train import NodeClassificationFullTrainer
-from autogl.module.nas import Darts, OneShotEstimator, SinglePathNodeClassificationSpace
-from autogl.module.nas.space.graph_nas import GraphNasNodeClassificationSpace
-from autogl.module.train import Acc
-from autogl.module.nas.algorithm.enas import Enas
-
-if __name__ == '__main__':
-    dataset = build_dataset_from_name('cora')
-    solver = AutoNodeClassifier(
-        feature_module='PYGNormalizeFeatures',
-        graph_models=[],
-        hpo_module=None,
-        ensemble_module=None,
-        default_trainer=NodeClassificationFullTrainer(
-            optimizer=torch.optim.Adam,
-            lr=0.01,
-            max_epoch=300,
-            early_stopping_round=300,
-            weight_decay=1e-4,
-            device="auto",
-            init=False,
-            feval=['acc'],
-            loss="nll_loss",
-            lr_scheduler_type=None,),
-        #nas_algorithms=[Enas()],
-        nas_algorithms=[Darts(num_epochs=200)],
-        #nas_spaces=[SinglePathNodeClassificationSpace(hidden_dim=32, ops=[GCNConv, GCNConv])],
-        nas_spaces=[GraphNasNodeClassificationSpace(hidden_dim=64,search_act_con=False,layer_number=4)],
-        nas_estimators=[OneShotEstimator()]
-    )
-    solver.fit(dataset)
-    solver.get_leaderboard().show()
-    out = solver.predict_proba()
-    print('acc on cora', Acc.evaluate(out, dataset[0].y[dataset[0].test_mask].detach().numpy()))