search

polarisZhao / PFLD-pytorch

PFLD pytorch Implementation
798 stars 197 forks source link

欧拉角检测不准， angle为检测，angle_gt为真实数据 #38

Closed a361251388 closed 3 years ago

a361251388 commented 4 years ago

angle = tensor([[-0.0873, 0.7688, -0.2588]], device='cuda:0') angle_gt = tensor([[ 88.0343, -60.7853, -62.0728]], device='cuda:0') angle = tensor([[-0.1598, 0.5773, -0.4115]], device='cuda:0') angle_gt = tensor([[ 66.4287, -53.0196, -49.0985]], device='cuda:0') angle = tensor([[-0.0510, 0.7076, -0.3719]], device='cuda:0') angle_gt = tensor([[ 48.0916, -45.6873, -17.9782]], device='cuda:0') angle = tensor([[ 0.0888, 0.7797, -0.3578]], device='cuda:0') angle_gt = tensor([[ 54.0094, -37.7794, -10.2092]], device='cuda:0') angle = tensor([[-0.0731, 0.8048, -0.0279]], device='cuda:0') angle_gt = tensor([[15.3467, 3.7500, 10.6802]], device='cuda:0') angle = tensor([[ 0.0906, 0.6620, -0.2479]], device='cuda:0') angle_gt = tensor([[ 79.5670, -63.5313, -39.0085]], device='cuda:0')

polarisZhao commented 4 years ago

这是弧度制和角度值的问题吧。 不过 solvePnP 这种方法来估计角度确实不大准，但是论文也是这么做。

futureisatyourhand commented 2 years ago

这是弧度制和角度值的问题吧。 不过 solvePnP 这种方法来估计角度确实不大准，但是论文也是这么做。

hello，I want to know how to issue the problem? why does this happen? Thanks!

wyfdodogod commented 1 year ago

这是弧度制和角度值的问题吧。 不过 solvePnP 这种方法来估计角度确实不大准，但是论文也是这么做。

hello，I want to know how to issue the problem? why does this happen? Thanks!

hi beauty, check his loss function u might know why, "weight_angle = torch.sum(1 - torch.cos(angle - euler_angle_gt), axis=1) "# funny np.cos(100-(100+n2np.pi))=1