Guocode

@hubutui sorry, it's your code ``` num = torch.sum(torch.mul(predict, target), dim=1) + self.smooth den = torch.sum(predict.pow(self.p) + target.pow(self.p), dim=1) + self.smooth ``` "+" in pytorch of a tensor and a...

and miss multiply 2, ``` self.smooth = 1 ... num = torch.sum(torch.mul(predict, target))*2 + self.smooth den = torch.sum(predict.pow(self.p) + target.pow(self.p)) + self.smooth ... return 1 - num/den ```

@diegovincent I have pointed out the difference, and I have released my code on my page, you can have a look at that.

Thanks very much for your reply and the implement. In fact I'm not so familiar with RNN but I think it's more reasonable to predict the next state by the...

Let's take a easy example, a current_state is like [(filter)16, (kernel)3, (filter)32, (kernel)(5)],encoded as [0,0,1,1] which may represent a two layers network.Then to predict the next state, in your code...

Unable to access dataset.Bad Gateway 502

> 不好意思，邮箱发不过去： > 链接: https://pan.baidu.com/s/1fOeqLor2mx8forE3L457hQ 密码: f4r7 兄弟能重新分享一下吗？感谢

Your landmark is very robust for most case like large pose and exaggerated expression, I have train my model on 300WLP, but it failed to detect often, can you share...

How do you think about regression based and heatmap based method, I use regression based method and add strong data augment as you mentioned, but when face box is not...

It's true, free orbit is more intuitive