xiaomingdaren123

Results 12 comments of xiaomingdaren123

@XiaogangYin @ycjing 我像第二作者要了数据集,发过来了,为什么test里面有trimaps,但是训练集里面没有trimaps?

@omoindrot Hi,omoindrot Thanks for your code,I meet some question, loss value is approximate of margin,i found that the distance is close to 0,I don't know how it was caused. Does...

I don't decrease the learning rate(learning rate is 0.001),if I decrease learning rate,training process become slow,batch_size is set to 96。Can triple loss be used directly for classification task? or the...

> Epoch 1/60 > 97/97 [==============================] - 24s - loss: 1.0072 - mAP: 0.1649 - val_loss: 0.9624 - val_mAP: 0.1296 > Epoch 2/60 > 97/97 [==============================] - 22s - loss:...

请问您看了原作者的代码没有,可不可以不用mean face shape这个文件?如果要用,使用自己的数据集,怎么制作mean face shape 啊?谢谢

这个网络为什么要分为两个阶段啊,第一个阶段等Loss不在降低,用这个阶段的模型去测试图片不能够得到landmarks的预测吗?

![default](https://user-images.githubusercontent.com/33368313/50964994-b4950780-150b-11e9-8497-8fd915321d02.png) ![default](https://user-images.githubusercontent.com/33368313/50964997-b5c63480-150b-11e9-8af4-e7e7ec066878.png) ![dinstance](https://user-images.githubusercontent.com/33368313/50965003-b9f25200-150b-11e9-9149-84956fa9883f.png) 首先,感谢您的回答 第一张图是我的网络结构,网络结构并不复杂,是一个7分类的问题,学习率已经设置为0.0001,采用Adam优化,但是还是会出现图二的训练情况,我将网络的最后一层求出的distance距离输出看了一下,发现acc等于0的时候我的dis矩阵所有元素基本都开始接近于0了,不知道是什么原因造成的?

@txiaoyun @d-acharya I apply the patch suggested in tensorflow_patch.txt file,but the train_loss is still nan,Could you give me some advice? Thank you.

@donghongwen 请问这个怎么训练啊,可以请教一下吗,深度学习小白,谢谢啦。

Thank you very much for your answer.