minigpt4/configs/datasets/video_chatgpt/default.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:
  video_chatgpt:
    # 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
      ann_paths: [datasets/training_datasets/video_text_data/video_instruct_100/VideoInstruct100K.json]
      vis_root: /ibex/project/c2090/datasets/VideoInstruct100K/
    valid:
      ann_path: "datasets/video_text_data/validation/all_datasets_samples_val_qa.json"
      videos_path: "/ibex/project/c2090/datasets/VideoInstruct100K/test_videos/all_datasets_samples_val"
      subtitles_path: "inference_subtitles"
      annotations_keys: ['question','answer','video_id']
      add_subtitles: True