print(num_person)

import argparse
import cv2
import mmcv
import numpy as np
import os
import os.path as osp
import shutil
import torch
import warnings
from scipy.optimize import linear_sum_assignment

from pyskl.apis import inference_recognizer, init_recognizer

try:
    from mmdet.apis import inference_detector, init_detector
except (ImportError, ModuleNotFoundError):
    def inference_detector(*args, **kwargs):
        pass

    def init_detector(*args, **kwargs):
        pass
    warnings.warn(
        'Failed to import `inference_detector` and `init_detector` from `mmdet.apis`. '
        'Make sure you can successfully import these if you want to use related features. '
    )

try:
    from mmpose.apis import inference_top_down_pose_model, init_pose_model, vis_pose_result
except (ImportError, ModuleNotFoundError):
    def init_pose_model(*args, **kwargs):
        pass

    def inference_top_down_pose_model(*args, **kwargs):
        pass

    def vis_pose_result(*args, **kwargs):
        pass

    warnings.warn(
        'Failed to import `init_pose_model`, `inference_top_down_pose_model`, `vis_pose_result` from '
        '`mmpose.apis`. Make sure you can successfully import these if you want to use related features. '
    )


try:
    import moviepy.editor as mpy
except ImportError:
    raise ImportError('Please install moviepy to enable output file')

def parse_args():
    parser = argparse.ArgumentParser(description='PoseC3D demo')
    # parser.add_argument('video', help='video file/url')
    # parser.add_argument('out_filename', help='output filename')
    parser.add_argument(
        '--config',
        default='../configs/posec3d/slowonly_r50_ntu120_xsub/joint.py',
        help='skeleton action recognition config file path')
    parser.add_argument(
        '--checkpoint',
        default='https://download.openmmlab.com/mmaction/pyskl/ckpt/posec3d/slowonly_r50_ntu120_xsub/joint.pth',
        help='skeleton action recognition checkpoint file/url')
    parser.add_argument(
        '--det-config',
        default='../demo/faster_rcnn_r50_fpn_1x_coco-person.py',
        help='human detection config file path (from mmdet)')
    parser.add_argument(
        '--det-checkpoint',
        default=('https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco-person/'
                 'faster_rcnn_r50_fpn_1x_coco-person_20201216_175929-d022e227.pth'),
        help='human detection checkpoint file/url')
    parser.add_argument(
        '--pose-config',
        default='../demo/hrnet_w32_coco_256x192.py',
        help='human pose estimation config file path (from mmpose)')
    parser.add_argument(
        '--pose-checkpoint',
        default='https://download.openmmlab.com/mmpose/top_down/hrnet/hrnet_w32_coco_256x192-c78dce93_20200708.pth',
        help='human pose estimation checkpoint file/url')
    parser.add_argument(
        '--det-score-thr',
        type=float,
        default=0.9,
        help='the threshold of human detection score')
    parser.add_argument(
        '--device', type=str, default='cuda:0', help='CPU/CUDA device option')
    args = parser.parse_args()
    return args

def frame_extraction(video_path, short_side):
    target_dir = osp.join('./tmp', osp.basename(osp.splitext(video_path)[0]))
    os.makedirs(target_dir, exist_ok=True)
    # Should be able to handle videos up to several hours
    frame_tmpl = osp.join(target_dir, 'img_{:06d}.jpg')
    vid = cv2.VideoCapture(video_path)
    frames = []
    frame_paths = []
    flag, frame = vid.read()
    cnt = 0
    new_h, new_w = None, None
    while flag:
        if new_h is None:
            h, w, _ = frame.shape
            new_w, new_h = mmcv.rescale_size((w, h), (short_side, np.Inf))

        frame = mmcv.imresize(frame, (new_w, new_h))

        frames.append(frame)
        frame_path = frame_tmpl.format(cnt + 1)
        frame_paths.append(frame_path)

        cv2.imwrite(frame_path, frame)
        cnt += 1
        flag, frame = vid.read()

    return frame_paths, frames
def detection_inference(args, frame_paths):
    """Detect human boxes given frame paths.

    Args:
        args (argparse.Namespace): The arguments.
        frame_paths (list[str]): The paths of frames to do detection inference.

    Returns:
        list[np.ndarray]: The human detection results.
    """
    model = init_detector(args.det_config, args.det_checkpoint, args.device)
    assert model is not None, ('Failed to build the detection model. Check if you have installed mmcv-full properly. '
                               'You should first install mmcv-full successfully, then install mmdet, mmpose. ')
    assert model.CLASSES[0] == 'person', 'We require you to use a detector trained on COCO'
    results = []
    print('Performing Human Detection for each frame')
    prog_bar = mmcv.ProgressBar(len(frame_paths))
    for frame_path in frame_paths:
        result = inference_detector(model, frame_path)
        # We only keep human detections with score larger than det_score_thr
        result = result[0][result[0][:, 4] >= args.det_score_thr]
        results.append(result)
        prog_bar.update()
    return results
def pose_inference(args, frame_paths, det_results):
    model = init_pose_model(args.pose_config, args.pose_checkpoint,
                            args.device)
    ret = []
    print('Performing Human Pose Estimation for each frame')
    prog_bar = mmcv.ProgressBar(len(frame_paths))
    for f, d in zip(frame_paths, det_results):
        # Align input format
        d = [dict(bbox=x) for x in list(d)]
        pose = inference_top_down_pose_model(model, f, d, format='xyxy')[0]
        ret.append(pose)
        prog_bar.update()
    return ret
def get_list_dimension(lst):
    if isinstance(lst, list):
        return 1 + (max(map(get_list_dimension, lst)) if lst else 0)
    return 0

def main():
    args = parse_args()
    frame_paths, original_frames = frame_extraction(r'D:\Project\pyskl-main\pyskl-main\demo\ntu_sample.avi',
                                                    480)
    num_frame = len(frame_paths)
    h, w, _ = original_frames[0].shape
    print(num_frame)
    config = mmcv.Config.fromfile(args.config)
    # print(config)
    model = init_recognizer(config, args.checkpoint, args.device)
    # print(model)
    det_results = detection_inference(args, frame_paths)
    # print(det_results)
    torch.cuda.empty_cache()
    pose_results = pose_inference(args, frame_paths, det_results)
    # print(pose_results)
    torch.cuda.empty_cache()
    tracking_inputs = [[pose['keypoints'] for pose in poses] for poses in pose_results]
    print("\n")
    # print(len(tracking_inputs))
    # print("OK")
    # print(tracking_inputs)
    # print(f"列表的维度: {get_list_dimension(tracking_inputs)}")
    num_person = max([len(x) for x in pose_results])
    print(num_person)
if __name__ == '__main__':
    main()

D:\Users\anaconda3\envs\openmmlab\python.exe D:\Project\pyskl-main\pyskl-main\Test\show_pose.py 
72
load checkpoint from local path: .cache\joint_f6bed715.pth
load checkpoint from http path: https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco-person/faster_rcnn_r50_fpn_1x_coco-person_20201216_175929-d022e227.pth
Performing Human Detection for each frame
[>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>] 72/72, 7.7 task/s, elapsed: 9s, ETA:     0sload checkpoint from http path: https://download.openmmlab.com/mmpose/top_down/hrnet/hrnet_w32_coco_256x192-c78dce93_20200708.pth
Performing Human Pose Estimation for each frame
[>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>] 72/72, 8.4 task/s, elapsed: 9s, ETA:     0s

2

Process finished with exit code 0
 

 

 采用的是

这就对应上了为什么num_person输出的是2

pyskl/demo/demo_skeleton.py at main · kennymckormick/pyskl · GitHub