hangon666
hangon666
> Hey there, > For the misalignment around nose, we also realize some limitation of this landmark based proxy estimator, we are developing our own proxy estimator, hopefully, we will...
@zomkey Hi, I am very interested in this work too, if convenient, could you send me your training codes so that I can learn the process better? My email address...
> How to get the evaluation results of Facewarehouse and MICC Florence? And are there differences compared with other methods in evaluation process? Could you provide an evaluation code? Thank...
@haha1958 @Laviyy Hello, did you re-train the network or test the given pre-trained model? My pytorch version is 0.4.1, but I can't load the given model generator_v0.pt
@haha1958 ，thanks for your reply, if convinient, could you share the re-trained model?
My version of nvidia.dali is 0.16.0, what's the version used in this project?
@opetrova thanks for your reply, I have changed my nvidia.dali version to 0.15.0, but when i try to test on pytorch==1.1.0, it seems dismatch, and when i test on pytorch==0.4.1,...
请问方便分享一下wing loss function部分的代码吗
非常感谢，由于我是初学者，我在学习尝试自己训练时出现 loss 是nan的情况，请问可以帮我看一下代码哪里出错了吗，谢谢！ ` def train(train_loader, model, criterion_wpdc, criterion_wing, optimizer_wpdc, optimizer_wing, epoch): batch_time = AverageMeter() data_time = AverageMeter() # 计算并存储平均值和当前值 losses = AverageMeter() model.train() end = time.time() # loader is...
非常感谢，请问您最终的loss大概在多少，我观察到初始的wingloss大约在30左右，而wpdcloss大约只有0.2，请问在您训练时也是这样的情况吗