meta/info.json

{
    "codebase_version": "v3.0",
    "fps": 20,
    "features": {
        "observation.images.robot0_agentview_left": {
            "dtype": "video",
            "shape": [
                256,
                256,
                3
            ],
            "names": [
                "height",
                "width",
                "channel"
            ],
            "video_info": {
                "video.fps": 20,
                "video.codec": "h264",
                "video.pix_fmt": "yuv420p",
                "video.is_depth_map": false,
                "has_audio": false
            },
            "info": {
                "video.height": 256,
                "video.width": 256,
                "video.codec": "h264",
                "video.pix_fmt": "yuv420p",
                "video.is_depth_map": false,
                "video.fps": 20,
                "video.channels": 3,
                "has_audio": false,
                "video.extra_options": null,
                "video.preset": null,
                "video.crf": null,
                "video.g": null,
                "video.fast_decode": null,
                "video.video_backend": "pyav"
            }
        },
        "observation.images.robot0_agentview_right": {
            "dtype": "video",
            "shape": [
                256,
                256,
                3
            ],
            "names": [
                "height",
                "width",
                "channel"
            ],
            "video_info": {
                "video.fps": 20,
                "video.codec": "h264",
                "video.pix_fmt": "yuv420p",
                "video.is_depth_map": false,
                "has_audio": false
            },
            "info": {
                "video.height": 256,
                "video.width": 256,
                "video.codec": "h264",
                "video.pix_fmt": "yuv420p",
                "video.is_depth_map": false,
                "video.fps": 20,
                "video.channels": 3,
                "has_audio": false,
                "video.extra_options": null,
                "video.preset": null,
                "video.crf": null,
                "video.g": null,
                "video.fast_decode": null,
                "video.video_backend": "pyav"
            }
        },
        "observation.images.robot0_eye_in_hand": {
            "dtype": "video",
            "shape": [
                256,
                256,
                3
            ],
            "names": [
                "height",
                "width",
                "channel"
            ],
            "video_info": {
                "video.fps": 20,
                "video.codec": "h264",
                "video.pix_fmt": "yuv420p",
                "video.is_depth_map": false,
                "has_audio": false
            },
            "info": {
                "video.height": 256,
                "video.width": 256,
                "video.codec": "h264",
                "video.pix_fmt": "yuv420p",
                "video.is_depth_map": false,
                "video.fps": 20,
                "video.channels": 3,
                "has_audio": false,
                "video.extra_options": null,
                "video.preset": null,
                "video.crf": null,
                "video.g": null,
                "video.fast_decode": null,
                "video.video_backend": "pyav"
            }
        },
        "action": {
            "dtype": "float32",
            "shape": [
                12
            ],
            "fps": 20
        },
        "observation.state": {
            "dtype": "float32",
            "shape": [
                16
            ],
            "names": [
                "state_0",
                "state_1",
                "state_2",
                "state_3",
                "state_4",
                "state_5",
                "state_6",
                "state_7",
                "state_8",
                "state_9",
                "state_10",
                "state_11",
                "state_12",
                "state_13",
                "state_14",
                "state_15"
            ],
            "fps": 20
        },
        "timestamp": {
            "dtype": "float32",
            "shape": [
                1
            ],
            "names": null
        },
        "frame_index": {
            "dtype": "int64",
            "shape": [
                1
            ],
            "names": null
        },
        "episode_index": {
            "dtype": "int64",
            "shape": [
                1
            ],
            "names": null
        },
        "index": {
            "dtype": "int64",
            "shape": [
                1
            ],
            "names": null
        },
        "task_index": {
            "dtype": "int64",
            "shape": [
                1
            ],
            "names": null
        },
        "language_persistent": {
            "dtype": "language",
            "shape": [
                1
            ],
            "names": null
        },
        "language_events": {
            "dtype": "language",
            "shape": [
                1
            ],
            "names": null
        }
    },
    "total_episodes": 32043,
    "total_frames": 29106226,
    "total_tasks": 4740,
    "chunks_size": 1000,
    "data_files_size_in_mb": 100,
    "video_files_size_in_mb": 200,
    "data_path": "data/chunk-{chunk_index:03d}/file-{file_index:03d}.parquet",
    "video_path": "videos/{video_key}/chunk-{chunk_index:03d}/file-{file_index:03d}.mp4",
    "robot_type": "robocasa",
    "splits": {
        "train": "0:32043"
    },
    "tools": [
        {
            "type": "function",
            "function": {
                "name": "say",
                "description": "Speak a short utterance to the user via the TTS executor.",
                "parameters": {
                    "type": "object",
                    "properties": {
                        "text": {
                            "type": "string",
                            "description": "The verbatim text to speak."
                        }
                    },
                    "required": [
                        "text"
                    ]
                }
            }
        }
    ]
}