SoftwareGift / FeatherNets_Face-Anti-spoofing-Attack-Detection-Challenge-CVPR2019

Code for 3rd Place Solution in Face Anti-spoofing Attack Detection Challenge @ CVPR2019,model only 0.35M!!! 1.88ms(CPU)
Other
928 stars 282 forks source link

validate问题 #24

Open 363325971 opened 5 years ago

363325971 commented 5 years ago

你好,我在训练完一个epoch后进行validata后出错,经查是在 _,predicted = torch.max(soft_output.data, 1) predicted = predicted.to('cpu').detach().numpy()

这里的predicted不是包含0,1的tensor,是一个这样的tensor Tensor: tensor([920, 744, 920, 818, 416, 920, 818, 920, 919, 920, 818, 818, 920, 974, 920, 855, 919, 744, 503, 818, 744, 920, 818, 684, 818, 503, 920, 919, 920, 818, 919, 974], device='cuda:0')

导致在后面计算confusion_matrix的时候无法正确计算tn, fp, fn, tp, 请问是哪里有问题吗? 我是从train_list里随机取的2000个样本做val_list的,其他地方没有改动

aloha000 commented 5 years ago

你好,请问你是用什么数据集跑的?原数据集我下载不了,求分享

363325971 commented 5 years ago

我用的就是百度云上的那个数据

aloha000 commented 5 years ago

百度云的链接好像已经没有了,可以发我一下吗?谢谢~

363325971 commented 5 years ago

Duplicate of #2 这里有啊

aloha000 commented 5 years ago

不知道为什么我这里readme没有显示 多谢~~

aloha000 commented 5 years ago

请问是应该把PAD文件夹放在data目录里,还是把PAD目录下的文件放在data里?可以加您微信聊一下吗?小白做起来有点费劲~

jiagh2010 commented 5 years ago

@aloha000 怎么做的??数据