project: name: adjective_aware_embedding task: multi_label_attribute_prediction primary_object_class: chair dataset: name: visual_genome root_dir: data/raw/visual_genome processed_dir: data/processed/visual_genome cache_dir: data/cache image_size: 224 num_workers: 8 pin_memory: true expected_primary_object_class: chair download: enabled: true force_download: false timeout_seconds: 120 retries: 3 chunk_size_bytes: 1048576 artifacts: - name: images_metadata url: https://homes.cs.washington.edu/~ranjay/visualgenome/data/dataset/image_data.json.zip filename: image_data.json.zip sha256: null - name: objects url: https://homes.cs.washington.edu/~ranjay/visualgenome/data/dataset/objects.json.zip filename: objects.json.zip sha256: null - name: attributes url: https://homes.cs.washington.edu/~ranjay/visualgenome/data/dataset/attributes.json.zip filename: attributes.json.zip sha256: null extraction: enabled: true force_extract: false safe_extract: true marker_file: .extract_complete archives: - image_data.json.zip - objects.json.zip - attributes.json.zip processing: output_format: parquet csv_fallback: true processing_report_file: processing_report.json label_vocab_file: label_vocab.json label_frequency_file: label_frequencies.json samples_file_parquet: samples.parquet samples_file_csv: samples.csv split_dir: splits unknown_label_token: __unknown__ keep_unmapped_attributes: false strict_chair_only: true splits: train: 0.8 val: 0.1 test: 0.1 stratify_by_attribute_groups: true multilabel_stratify: true stratify_fallback: iterative_bucket split_seed: 42 attributes: groups: color: - blue - red - white - black material: - wooden - plastic - metal condition: - broken - clean - dirty - old min_support: 200 lowercase: true lemmatize: true synonym_map: wood: wooden damaged: broken filtering: drop_empty_labels: true deduplicate_images: true keep_only_primary_object: chair max_samples_per_attribute: null augmentation: enabled: true horizontal_flip_prob: 0.5 color_jitter_prob: 0.2 random_resized_crop_scale: - 0.8 - 1.0