github-luffy
commented
3 years ago I have tried both with "pretrained_model/mobileNetV2_0.25.pth" and without this pretrained model for retraining the model for common, challenge and fullset.
However, losses never goes down to below 30, neither from pretrained or retrained from initial-scratch. On the other hand, I tried to removed the training part of the code from train_model.py see this https://github.com/epoc88/PFLD_68pts_Pytorch/blob/master/test_NME.py
I did not add any pretrained model, but I still got some NME result..
Test epochs: 3 Loss 0.094 mean error and failure rate mean error : 0.061 failure rate: L1 0.161
So I am a bit confused...
The issue could be related to optimizer and gradient decent., or loss function WingLoss is good for fine tuning, but PFLF's MSE could be good in the beginning.
Here is a Chinese paper discussing the performance of PFLD on 300W, especially the loss function https://jishuin.proginn.com/p/763bfbd29621
One more thing, it is worth to mention that the default code for training is "common subset" for validation during training (i.e. without ibug images). There are common, challenge, fullset as validation subset.
我已经尝试了使用“pretrained_model/mobileNetV2_0.25.pth”和没有此预训练模型的重新训练模型，以进行普通、挑战和全集的重新训练。
然而，损失从不低于30 ，无论是从最初的训练或再训练。 另一方面，我试图从train_model.py中删除代码的训练部分 看看这个 https://github.com/epoc88/PFLD_68pts_Pytorch/blob/master/test_NME.py
我没有添加任何预先训练的模型，但我仍然得到了一些NME的结果。
测试阶段：3损耗0.094 平均误差和故障率 平均误差： 0.061 失效率：L1 0.161
所以我有点困惑...
这个问题可能与_optimizer_和梯度下降法有关。
下文是一篇关于300W的PFLD性能，特别是损耗函数的中文论文。 https://jishuin.proginn.com/p/763bfbd29621
这是我用您的代码修改后训练的MobileNetV2_0.25模型来测算的结果
论文结果 Speed on CPU (1.25ms) Model Size (2MB) NME (ION) Common (3.03) NME (ION) Challenge (5.15 ) NME (ION) Fullset (3.45) AUC (0.80) 我们代码的结果, 206 1.1 4.74 7.95 5.25 0.4889 (fullset) 主要差别，论文速度1.25ms, 我们的是200ms, MobileV2_0.25 的尺寸也不一样，论文是2.1MB， 我们pretrained_model 是1.1MB, 这个不是官方的pretrained model?
还有一点，值得一提的是，训练的默认代码是训练期间验证的“公共子集”（即。没有ibug图片）。有共同的，挑战的，全集作为验证子集。
感谢做了好多工作，简单回答以上几个问题： 1.损失从不低于30 ？可能是损失函数的设计，你可以修改或更换下损失跑跑看 2.没有添加任何预先训练的模型，得到了一些NME的结果？没设置模型，但是代码给了模型默认的路径，你确保这个有没有? 3.论文结果？可能跟论文结果有较多出入，MobileNetV2_0.25模型有些不同，你可以根据论文的参数设置网络，然后跑跑看
epoc88
huangzhenjie
I have tried both with "pretrained_model/mobileNetV2_0.25.pth" and without this pretrained model for retraining the model for common, challenge and fullset.
However, losses never goes down to below 30, neither from pretrained or retrained from initial-scratch. On the other hand, I tried to removed the training part of the code from train_model.py see this https://github.com/epoc88/PFLD_68pts_Pytorch/blob/master/test_NME.py
I did not add any pretrained model, but I still got some NME result..
Test epochs: 3 Loss 0.094 mean error and failure rate mean error : 0.061 failure rate: L1 0.161
So I am a bit confused...
The issue could be related to optimizer and gradient decent., or loss function WingLoss is good for fine tuning, but PFLF's MSE could be good in the beginning.
Here is a Chinese paper discussing the performance of PFLD on 300W, especially the loss function https://jishuin.proginn.com/p/763bfbd29621
One more thing, it is worth to mention that the default code for training is "common subset" for validation during training (i.e. without ibug images). There are common, challenge, fullset as validation subset.
我已经尝试了使用“pretrained_model/mobileNetV2_0.25.pth”和没有此预训练模型的重新训练模型，以进行普通、挑战和全集的重新训练。
然而，损失从不低于30 ，无论是从最初的训练或再训练。 另一方面，我试图从train_model.py中删除代码的训练部分 看看这个 https://github.com/epoc88/PFLD_68pts_Pytorch/blob/master/test_NME.py
我没有添加任何预先训练的模型，但我仍然得到了一些NME的结果。
测试阶段：3损耗0.094 平均误差和故障率 平均误差： 0.061 失效率：L1 0.161
所以我有点困惑...
这个问题可能与损耗函数 和 梯度下降法有关。**
下文是一篇关于300W的PFLD性能，特别是损耗函数的中文论文。 https://jishuin.proginn.com/p/763bfbd29621
这是我用您的代码修改后训练的MobileNetV2_0.25模型来测算的结果
主要差别，论文速度1.25ms, 我们的是200ms, MobileV2_0.25 的尺寸也不一样，论文是2.1MB， 我们pretrained_model 是1.1MB, 这个不是官方的pretrained model?
还有一点，值得一提的是，训练的默认代码是训练期间验证的“公共子集”（即。没有ibug图片）。有共同的，挑战的，全集作为验证子集。