hrnet笔记

这个有简单代码:

https://github.com/lizhe960118/Deep-Learning

 

High resolution 高分辨率网络

中科大和微软亚洲研究院,发布了新的人体姿态估计模型,刷新了三项COCO纪录,还中选了CVPR 2019。

这个名叫HRNet的神经网络,拥有与众不同的并联结构,可以随时保持高分辨率表征,不只靠从低分辨率表征里,恢复高分辨率表征。如此一来,姿势识别的效果明显提升:

在COCO数据集的关键点检测、姿态估计、多人姿态估计这三项任务里,HRNet都超越了所有前辈。

 

https://github.com/icicle4/SuperResulation-HRNet

 

人体姿态,有权重

https://github.com/stefanopini/simple-HRNet

这个网络384*288,cpu1.8s

1070 gpu 130ms,特别慢

data=torch.ones(1, 3, 384*3, 288*3).to(device) 

分辨率*3,则需要270ms

if __name__ == '__main__':
    # model = HRNet(48, 17, 0.1)
    model = HRNet(32, 17, 0.1)

    # print(model)

    # model.load_state_dict(
    #     # torch.load('./weights/pose_hrnet_w48_384x288.pth')
    #     torch.load('./weights/pose_hrnet_w32_256x192.pth')
    # )
    # print('ok!!')

    if torch.cuda.is_available():
        torch.backends.cudnn.deterministic = True
        device = torch.device('cuda:0')
    else:
        device = torch.device('cpu')

    print(device)

    model = model.to(device)
    data=torch.ones(1, 3, 384, 288).to(device)
    import time
    for i in range(20):
        start=time.time()
        y = model(data)
        print(y.shape,'time',time.time()-start)

https://github.com/HRNet/HigherHRNet-Human-Pose-Estimation

人脸关键点:224 100ms

https://blog.csdn.net/jacke121/article/details/100640305

分割:

https://github.com/HRNet/HRNet-Semantic-Segmentation

https://github.com/HRNet/HRNet-FCOS

能检测摄像头

https://github.com/HRNet/HRNet-FCOS/blob/master/demo/webcam.py

你可能感兴趣的:(姿态检测,深度学习)