lavis/configs/datasets/conceptual_caption/defaults_3m.yaml

 # Copyright (c) 2022, salesforce.com, inc.
 # All rights reserved.
 # SPDX-License-Identifier: BSD-3-Clause
 # For full license text, see the LICENSE file in the repo root or https://opensource.org/licenses/BSD-3-Clause

datasets:
  conceptual_caption_3m:
    # data_dir: ${env.data_dir}/datasets
    data_type: images # [images|videos|features]

    build_info:
      # Be careful not to append minus sign (-) before split to avoid itemizing
      annotations:
        train:
          url:
              - /export/home/workspace/datasets/cc3m.json
          storage:
              - conceptual_caption/annotations/cc3m.json
      images:
          storage: conceptual_caption/images