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