Skip to content

Commit 615d02d

Browse files
committed
fix typo in notebook
1 parent 9e6c885 commit 615d02d

File tree

1 file changed

+2
-18
lines changed

1 file changed

+2
-18
lines changed

examples/From_ABC_to_BayesFlow.ipynb

Lines changed: 2 additions & 18 deletions
Original file line numberDiff line numberDiff line change
@@ -608,7 +608,7 @@
608608
},
609609
"outputs": [],
610610
"source": [
611-
"inference_net = bf.networks.ConsistencyModel(total_stps=epochs*num_batches_per_epoch)"
611+
"inference_net = bf.networks.ConsistencyModel(total_steps=epochs*num_batches_per_epoch)"
612612
]
613613
},
614614
{
@@ -933,13 +933,6 @@
933933
"source": [
934934
"We have yet to fully explore the potential of amortized inference. For higher-dimensional problems, we can train a summary network jointly with the inference network, eliminating the need to manually design summary statistics as required in ABC. Additionally, the trained approximator can be seamlessly transferred to new datasets, enabling inference without retraining. Even in this simple example, we see that training the approximator required fewer simulations than running the ABC, which is particularly beneficial for computationally expensive simulators.\n"
935935
]
936-
},
937-
{
938-
"cell_type": "code",
939-
"execution_count": null,
940-
"metadata": {},
941-
"outputs": [],
942-
"source": []
943936
}
944937
],
945938
"metadata": {
@@ -950,16 +943,7 @@
950943
"name": "python3"
951944
},
952945
"language_info": {
953-
"codemirror_mode": {
954-
"name": "ipython",
955-
"version": 3
956-
},
957-
"file_extension": ".py",
958-
"mimetype": "text/x-python",
959-
"name": "python",
960-
"nbconvert_exporter": "python",
961-
"pygments_lexer": "ipython3",
962-
"version": "3.8.8"
946+
"name": "python"
963947
}
964948
},
965949
"nbformat": 4,

0 commit comments

Comments
 (0)