Commit 7d5b1279 authored by yurievnamaria's avatar yurievnamaria
Browse files

Bug fix: previously, when using classification GraphConvModel for prospective data prediction 

without passing activity ("tasks") raised an error.
Now we can pass just an empty list and prediction will work OK
parent 8ba35f6a

deepchem/models/graph_models.py

+1 −1
Original line number Diff line number Diff line
@@ -980,7 +980,7 @@ class GraphConvModel(KerasModel): 
          batch_size=self.batch_size,

          deterministic=deterministic,

          pad_batches=pad_batches):

        if self.mode == 'classification':

        if y_b is not None and self.mode == 'classification':

          y_b = to_one_hot(y_b.flatten(), self.n_classes).reshape(

              -1, self.n_tasks, self.n_classes)

        multiConvMol = ConvMol.agglomerate_mols(X_b)

CRA Git | Maintained and supported by SUSTech CRA and CCSE