Description #

Video resolution adjustment

Key features #

• Intelligent resolution adjustment within a specified range
• Supports multiple aspect ratio preservation strategies
• Allows control of video quality and encoding parameters
• Keeps audio stream unaffected
• Supports path input, binary input, and TOS output

Format support #

• MP4 (.mp4)
• AVI (.avi)
• MOV (.mov)
• MKV (.mkv)
• Other common video formats

Encoding modes #

• CPU encoding (libx264): Quality prioritized, high compression efficiency, slower speed
• GPU encoding (h264_nvenc): Fast speed, suitable for batch processing, quality slightly lower than libx264 (at the same bitrate), compression efficiency is somewhat lower, files may be larger

Operator parameters #

Input #

Output #

Column for adjusted video paths

Parameters #

If a parameter does not have a default value, it is required

Examples #

The following code demonstrates how to use Daft (for distributed scenarios) to run the operator for intelligent video resolution adjustment.

from __future__ import annotations

import os

import daft
from daft import col
from daft.las.functions.udf import las_udf
from daft.las.functions.video import VideoResizeResolution

if __name__ == "__main__":

    # Videos with modified resolution will be saved to the specified TOS path. Therefore, you need to set environment variables to ensure write permissions to TOS, including: ACCESS_KEY, SECRET_KEY, TOS_ENDPOINT, TOS_REGION, TOS_TEST_DIR
    TOS_DIR = os.getenv("TOS_TEST_DIR", "tos_bucket")
    output_tos_dir = f"tos://{TOS_DIR}/video/video_resize_resolution"

    if os.getenv("DAFT_RUNNER", "native") == "ray":
        import logging

        import ray

        def configure_logging():
            logging.basicConfig(
                level=logging.INFO,
                format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
                datefmt="%Y-%m-%d %H:%M:%S.%s".format(),
            )
            logging.getLogger("tracing.span").setLevel(logging.WARNING)
            logging.getLogger("daft_io.stats").setLevel(logging.WARNING)
            logging.getLogger("DaftStatisticsManager").setLevel(logging.WARNING)
            logging.getLogger("DaftFlotillaScheduler").setLevel(logging.WARNING)
            logging.getLogger("DaftFlotillaDispatcher").setLevel(logging.WARNING)

        ray.init(dashboard_host="0.0.0.0", runtime_env={"worker_process_setup_hook": configure_logging})
        daft.set_runner_ray()

    daft.set_execution_config(actor_udf_ready_timeout=600)
    daft.set_execution_config(min_cpu_per_task=0)

    tos_dir_url = os.getenv("TOS_DIR_URL", "las-cn-beijing-public-online.tos-cn-beijing.volces.com")
    samples = {
        "video_path": [
            f"https://{tos_dir_url}/public/shared_video_dataset/eating_56.mp4"
        ]
    }
    ds = daft.from_pydict(samples)

    constructor_kwargs = {
        "output_tos_dir": output_tos_dir,
        "min_width": 1280,
        "max_width": 2560,
        "min_height": 720,
        "max_height": 1440,
        "force_original_aspect_ratio_type": "decrease",
        "rank": None,
    }

    ds = ds.with_column(
        "resized_video_path",
        las_udf(VideoResizeResolution, construct_args=constructor_kwargs, num_gpus=1, batch_size=1, concurrency=1)(
            col("video_path")
        ),
    )

    ds.show()
    # ╭────────────────────────────────┬──────────────────────────────────╮
    # │ video_path                     ┆ resized_video_path               │
    # │ ---                            ┆ ---                              │
    # │ Utf8                           ┆ Utf8                             │
    # ╞════════════════════════════════╪══════════════════════════════════╡
    # │ https://las-cn-beijing-publi-… ┆ tos://tos_bucket/video_resize…   │
    # ╰────────────────────────────────┴──────────────────────────────────╯