import os
from argparse import ArgumentParser

import cv2

from mmpose.apis import (inference_bottom_up_pose_model, init_pose_model,
                         vis_pose_result)
from mmcv import Config, DictAction
from mmcv.parallel import MMDataParallel, MMDistributedDataParallel
from mmcv.runner import get_dist_info, init_dist, load_checkpoint
from models import build_posenet
def main():
    """Visualize the demo images."""
    parser = ArgumentParser()
    parser.add_argument('pose_config', help='Config file for pose')
    parser.add_argument('pose_checkpoint', help='Checkpoint file for pose')
    parser.add_argument('--video-path', type=str, help='Video path')
    parser.add_argument(
        '--show',
        action='store_true',
        default=False,
        help='whether to show visualizations.')
    parser.add_argument(
        '--out-video-root',
        default='',
        help='Root of the output video file. '
        'Default not saving the visualization video.')
    parser.add_argument(
        '--device', default='cuda:0', help='Device used for inference')
    parser.add_argument(
        '--kpt-thr', type=float, default=0.3, help='Keypoint score threshold')

    args = parser.parse_args()
    
    assert args.show or (args.out_video_root != '')
    cfg = Config.fromfile(args.pose_config)

    #if args.cfg_options is not None:
    #    cfg.merge_from_dict(args.cfg_options)

    # set cudnn_benchmark
    if cfg.get('cudnn_benchmark', False):
        torch.backends.cudnn.benchmark = True
    cfg.model.pretrained = None
    cfg.data.test.test_mode = True
    model = build_posenet(cfg.model)
    fp16_cfg = cfg.get('fp16', None)
    if fp16_cfg is not None:
        wrap_fp16_model(model)
    load_checkpoint(model, args.pose_checkpoint, map_location='cpu')
    #model = MMDataParallel(model, device_ids=[0])
    # build the pose model from a config file and a checkpoint file
    #pose_model = init_pose_model(
    #    args.pose_config, args.pose_checkpoint, device=args.device.lower())

    dataset = cfg.data['test']['type']
    #assert (dataset == 'BottomUpCocoDataset')

    cap = cv2.VideoCapture(args.video_path)

    if args.out_video_root == '':
        save_out_video = False
    else:
        os.makedirs(args.out_video_root, exist_ok=True)
        save_out_video = True

    if save_out_video:
        fps = cap.get(cv2.CAP_PROP_FPS)
        size = (int(cap.get(cv2.CAP_PROP_FRAME_WIDTH)),
                int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT)))
        fourcc = cv2.VideoWriter_fourcc(*'mp4v')
        videoWriter = cv2.VideoWriter(
            os.path.join(args.out_video_root,
                         f'vis_{os.path.basename(args.video_path)}'), fourcc,
            fps, size)

    # optional
    return_heatmap = False

    # e.g. use ('backbone', ) to return backbone feature
    output_layer_names = None

    while (cap.isOpened()):
        flag, img = cap.read()
        if not flag:
            break

        pose_results, returned_outputs = inference_bottom_up_pose_model(
            model,
            img,
            return_heatmap=return_heatmap,
            outputs=output_layer_names)

        # show the results
        vis_img = vis_pose_result(
            pose_model,
            img,
            pose_results,
            dataset=dataset,
            kpt_score_thr=args.kpt_thr,
            show=False)

        if args.show:
            cv2.imshow('Image', vis_img)

        if save_out_video:
            videoWriter.write(vis_img)

        if cv2.waitKey(1) & 0xFF == ord('q'):
            break

    cap.release()
    if save_out_video:
        videoWriter.release()
    cv2.destroyAllWindows()


if __name__ == '__main__':
    main()