'GNNExplainer' object has no attribute 'node_idx' with BA_shapes

[scottdd204]

I have tried working back through the problem but more issues crop up, this is only the case with BA_shapes @Oceanusity

~/DIG$ DATASETS=ba_shapes

~/DIG$ HYDRA_FULL_ERROR=1 python -m benchmarks.xgraph.gnn_explainer datasets=$DATASETS explainers=gnn_explainer record_filename=/home/scott/DIG/benchmarks/xgraph/results/GNNExplainer
/home/scott/DIG/benchmarks/xgraph/gnn_explainer.py:18: UserWarning:
The version_base parameter is not specified.
Please specify a compatability version level, or None.
Will assume defaults for version 1.1
@hydra.main(config_path="config", config_name="config")
/home/scott/.local/lib/python3.8/site-packages/hydra/_internal/defaults_list.py:251: UserWarning: In 'config': Defaults list is missing _self_. See https://hydra.cc/docs/1.2/upgrades/1.0_to_1.1/default_composition_order for more information
warnings.warn(msg, UserWarning)
/home/scott/.local/lib/python3.8/site-packages/hydra/_internal/hydra.py:119: UserWarning: Future Hydra versions will no longer change working directory at job runtime by default.
See https://hydra.cc/docs/1.2/upgrades/1.1_to_1.2/changes_to_job_working_dir/ for more information.
ret = run_job(
models:
gnn_saving_dir: /home/scott/DIG/benchmarks/xgraph/checkpoints
gnn_name: gcn
param:
learning_rate: 0.05
weight_decay: 0.0005
milestones: None
gamma: None
batch_size: 1
num_epochs: 400
num_early_stop: 0
gnn_latent_dim:
- 20
- 20
- 20
gnn_dropout: 0.0
add_self_loop: false
gcn_adj_normalization: false
gnn_emb_normalization: false
graph_classification: false
node_classification: true
gnn_nonlinear: relu
readout: identity
fc_latent_dim: []
fc_dropout: 0.0
fc_nonlinear: relu
concate: false
datasets:
dataset_root: /home/scott/DIG/benchmarks/xgraph/datasets
dataset_name: ba_shapes
explainers:
explanation_result_dir: /home/scott/DIG/benchmarks/xgraph/results
sparsity: 0.5
param:
lr: 0.01
epochs: 100
coff_size: 0.1
coff_ent: 0.1
random_seed: 0
device_id: 0
record_filename: /home/scott/DIG/benchmarks/xgraph/result_jsons/ba_shapes.json

/home/scott/miniconda3/envs/DIG/lib/python3.8/site-packages/torch_geometric/data/in_memory_dataset.py:300: UserWarning: It is not recommended to directly access the internal storage format data of an 'InMemoryDataset'. If you are absolutely certain what you are doing, access the internal storage via InMemoryDataset._data instead to suppress this warning. Alternatively, you can access stacked individual attributes of every graph via dataset.{attr_name}.
warnings.warn(msg)
Error executing job with overrides: ['datasets=ba_shapes', 'explainers=gnn_explainer', 'record_filename=/home/scott/DIG/benchmarks/xgraph/results/GNNExplainer', 'explainers=gnn_explainer', 'datasets.dataset_root=/home/scott/DIG/benchmarks/xgraph/datasets', 'models.gnn_saving_dir=/home/scott/DIG/benchmarks/xgraph/checkpoints', 'explainers.explanation_result_dir=/home/scott/DIG/benchmarks/xgraph/results', 'record_filename=/home/scott/DIG/benchmarks/xgraph/result_jsons']
Traceback (most recent call last):
File "/home/scott/miniconda3/envs/DIG/lib/python3.8/runpy.py", line 194, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/home/scott/miniconda3/envs/DIG/lib/python3.8/runpy.py", line 87, in _run_code
exec(code, run_globals)
File "/home/scott/DIG/benchmarks/xgraph/gnn_explainer.py", line 216, in
pipeline()
File "/home/scott/.local/lib/python3.8/site-packages/hydra/main.py", line 94, in decorated_main
_run_hydra(
File "/home/scott/.local/lib/python3.8/site-packages/hydra/_internal/utils.py", line 394, in _run_hydra
_run_app(
File "/home/scott/.local/lib/python3.8/site-packages/hydra/_internal/utils.py", line 457, in _run_app
run_and_report(
File "/home/scott/.local/lib/python3.8/site-packages/hydra/_internal/utils.py", line 223, in run_and_report
raise ex
File "/home/scott/.local/lib/python3.8/site-packages/hydra/_internal/utils.py", line 220, in run_and_report
return func()
File "/home/scott/.local/lib/python3.8/site-packages/hydra/_internal/utils.py", line 458, in
lambda: hydra.run(
File "/home/scott/.local/lib/python3.8/site-packages/hydra/_internal/hydra.py", line 132, in run
_ = ret.return_value
File "/home/scott/.local/lib/python3.8/site-packages/hydra/core/utils.py", line 260, in return_value
raise self._return_value
File "/home/scott/.local/lib/python3.8/site-packages/hydra/core/utils.py", line 186, in run_job
ret.return_value = task_function(task_cfg)
File "/home/scott/DIG/benchmarks/xgraph/gnn_explainer.py", line 138, in pipeline
gnn_explainer(data.x, data.edge_index,
File "/home/scott/.local/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/home/scott/.local/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1520, in _call_impl
return forward_call(*args, **kwargs)
File "/home/scott/DIG/dig/xgraph/method/gnnexplainer.py", line 159, in forward
edge_mask = self.gnn_explainer_alg(x, edge_index, ex_label).sigmoid()
File "/home/scott/DIG/dig/xgraph/method/gnnexplainer.py", line 96, in gnn_explainer_alg
loss = self.loss(raw_preds, ex_label)
File "/home/scott/DIG/dig/xgraph/method/gnnexplainer.py", line 58, in loss
loss = cross_entropy_with_logit(raw_preds[self.node_idx].reshape(1, -1), x_label)
File "/home/scott/.local/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1688, in getattr
raise AttributeError(f"'{type(self).name}' object has no attribute '{name}'")
AttributeError: 'GNNExplainer' object has no attribute 'node_idx'