diff --git a/README.md b/README.md
index 6101982..5bf552f 100644
--- a/README.md
+++ b/README.md
@@ -39,18 +39,30 @@ trainval_balanced_programs.json
> GQA dictionaries: `gqa_all_attributes.json` and `gqa_all_vocab_classes` are also adapted from [https://github.com/wenhuchen/Meta-Module-Network](https://github.com/wenhuchen/Meta-Module-Network)
## Generate Query Masks
-- generates full_relations_df.pkl if not already present
-- generates query masks for all relations with more than 1000 samples
+> All 37 generated query masks are available in [relations.zip](relations.zip) as numpy files
+
+```python
+# loading a query mask with numpy
+import numpy as np
+rel = 'to_the_right_of'
+path = f'relations/{rel}.npy'
+mask = np.load(path)
+mask = mask > 0.05 # binary mask
+```
+If you want to run the generation process, run:
```shell
python generate_query_masks.py
```
+- generates full_relations_df.pkl if not already present
+- generates query masks for all relations with more than 1000 samples
+
## Pipeline
Execute Pipeline for all samples in GQA: train_balanced (with `TEST=False`) or validation_balanced (with `TEST=True`)
```shell
python run_programs.py
```
-For visualizing samples with full all pipeline steps see [VSA4VQA_examples.ipynb](VSA4VQA_examples.ipynb)
+For visualizing samples with all pipeline steps see [VSA4VQA_examples.ipynb](VSA4VQA_examples.ipynb)
## Citation
Please consider citing this paper if you use VSA4VQA or parts of this publication in your research:
diff --git a/relations.zip b/relations.zip
new file mode 100644
index 0000000..07c0b71
Binary files /dev/null and b/relations.zip differ