_target_: src.datasets.modalities.caption_dataset.CaptionDataset name: caption dataset_dir: ${dataset.dataset_dir} segment_dir: ${dataset.dataset_dir}/cam_segments raw_caption_dir: ${dataset.dataset_dir}/caption feat_caption_dir: ${dataset.dataset_dir}/caption_clip num_segments: 27 num_feats: 512 num_cams: ${dataset.standardization.num_cams} sequential: ${diffuser.network.module.clip_sequential} max_feat_length: 77