Video Demo Code Messed Up After Recent Commit

[varungupta31]

A recent commit (by @ZhangYuanhan-AI) on the Video Demo Code has added multiple syntactical bugs.

The commit https://github.com/LLaVA-VL/LLaVA-NeXT/commit/066ea451b263f408a00d5fbfa0daa1ef71c33796

def parse_args():
    """
    Parse command-line arguments.
    """
    parser = argparse.ArgumentParser()

    # Define the command-line arguments
    parser.add_argument("--video_path", help="Path to the video files.", required=True)
    parser.add_argument("--output_dir", help="Directory to save the model results JSON.", required=True)
    parser.add_argument("--output_name", help="Name of the file for storing results JSON.", required=True)
    parser.add_argument("--model-path", type=str, default="facebook/opt-350m")
    parser.add_argument("--model-base", type=str, default=None)
    parser.add_argument("--conv-mode", type=str, default=None)
    parser.add_argument("--chunk-idx", type=int, default=0)
    parser.add_argument("--mm_resampler_type", type=str, default="spatial_pool")
    parser.add_argument("--mm_spatial_pool_stride", type=int, default=4)
    parser.add_argument("--mm_spatial_pool_out_channels", type=int, default=1024)
    parser.add_argument("--mm_spatial_pool_mode", type=str, default="average")
    parser.add_argument("--image_aspect_ratio", type=str, default="anyres")
    parser.add_argument("--image_grid_pinpoints", type=str, default="[(224, 448), (224, 672), (224, 896), (448, 448), (448, 224), (672, 224), (896, 224)]")
    parser.add_argument("--mm_patch_merge_type", type=str, default="spatial_unpad")
    parser.add_argument("--overwrite", type=lambda x: (str(x).lower() == 'true'), default=True)
    parser.add_argument("--for_get_frames_num", type=int, default=4)
    parser.add_argument("--load_8bit",  type=lambda x: (str(x).lower() == 'true'), default=False)
    parser.add_argument("--prompt", type=str, default=None) 
    parser.add_argument("--api_key", type=str, help="OpenAI API key")
    parser.add_argument("--mm_newline_position", type=str, default="no_token")
    parser.add_argument("--force_sample", type=lambda x: (str(x).lower() == 'true'), default=False)
    parser.add_argument("--add_time_instruction", type=str, default=False)
    return parser.parse_args()

    def load_video(video_path,args):
        if max_frames_num == 0:
            return np.zeros((1, 336, 336, 3))
        vr = VideoReader(video_path, ctx=cpu(0),num_threads=1)
        total_frame_num = len(vr)
        video_time = total_frame_num / vr.get_avg_fps()
        fps = round(vr.get_avg_fps()/fps)
        frame_idx = [i for i in range(0, len(vr), fps)]
        frame_time = [i/fps for i in frame_idx]
        if len(frame_idx) > args.for_get_frames_num or args.force_sample:
            sample_fps = max_frames_num
            uniform_sampled_frames = np.linspace(0, total_frame_num - 1, sample_fps, dtype=int)
            frame_idx = uniform_sampled_frames.tolist()
            frame_time = [i/vr.get_avg_fps() for i in frame_idx]
        frame_time = ",".join([f"{i:.2f}s" for i in frame_time])
        spare_frames = vr.get_batch(frame_idx).asnumpy()
        # import pdb;pdb.set_trace()

        return spare_frames,frame_time,video_time

the def load_video has inconsistent tab spaces.

Further, to name a few:

• max_frames_num is not defined anywhere.
• fps is referenced before the assignment

[ZhangYuanhan-AI]

https://github.com/LLaVA-VL/LLaVA-NeXT/pull/205

Waiting for this merge.

[varungupta31]

I see, thank you @ZhangYuanhan-AI :)