xiaomingdaren123

Results 7 issues of xiaomingdaren123

hi,MarekKowalski ,In the CropResizeRotate,I don't understand the role of destShape.Why is this step to calculate the transformation from initshape to destshape? In the network,the initLandmarks(S0) is the destshape?thanks

hi,MarekKowalski,I used the code you provided to train the model. When I tested the image, it didn't respond. Using your model (DAN.npz) also meet same problem,but No problem with other...

hi,MarekKowalski ,thank you for your code about deep alignment network.but i have some trouble about it ,i hope you could help me. 1、When I download the 300-W dataset based on...

hi,omoindrot I have encountered some problems,after training for a while,pairwise_dist drops to 0,loss is near the margin and can't go down,visualize the training set and discover that they are all...

首先非常感谢您提供的代码,有两个问题希望您能提供帮助 1、在我用batch_hard_triplet_loss方法训练手写数字网络时,我发现如果我的网络不加BN层,训练一会之后loss就会固定在margin的大小不在下降,并且acc(acc使用KNN求得)变成了0,我查看了一下_pairwise_distances,发现距离矩阵也差不多都变成了?这是什么原因造成的呢,必须要加bn层吗? 2、我将batch_hard_triplet_loss用在其他分类任务当中,网络采用VGG网络以及自己设计的简单网络,我发现就算我加了BN层,两个网络也会出现上述情况,我只用了三元组损失并没有使用其他损失,不知道这是什么原因?跟网络的大小或者分类任务的难易有关吗? 谢谢,希望您能回答。

请问一下,triplet loss之前都要进行L2归一化处理吗?我看到facenet 网络的最后使用了L2归一化得到embeddings,但是有的代码又没有使用L2归一化?

您好, 最近我训练triplet_loss的时候遇到了一些问题,不知道怎么解决。我的网络采用的是vgg网络,然后没有进行softmax预训练,直接用triplet_loss进行训练的会出现ap,an变成0的情况,在网上查了以下资料说是训练崩塌,所有点都聚在了一起,降低学习率训练太慢了也没有解决问题,想请教一下您是怎么解决这种情况的?是不是一定要softmax预训练?谢谢!