SuyueLiu

Can this work be extended to RGB inputs?

1

Thanks for your impressive work. I only have RGB images, Can this work be extended to RGB inputs?

下载安卓版本的fom demo，Android studio编译完成之后提示Cannot resolve symbol 'PaddlePredictor'等错误，这些错误都指向import com.baidu.paddle.lite报错，请教一下我是不是漏掉了哪些步骤？如何解决这个问题？ 另外，我下载好编译好的预测库之后应该放到哪里？如何配置？ 第一次使用paddle相关的东西，不太熟悉，还请大佬多指点指点！

onnx_helper error

4

when I run onnx_helper to check the trained onnx model(generate by the default code), I got an error:  Traceback (most recent call last): File "onnx_helper.py", line 251, in err...

How to find the best similarity threshold on my private dataset?

3

Hi, thanks for your impressive work on face recognition. I have trained an FR model on the MS1MV2 dataset with ArcFace and test on my private dataset, I noticed that...

arcface_torch: There are periodic, sudden drops in losses

6

 backbone: mbf loss: arcface dataset: glint (msra + asian celeb) lr = 0.1 wd = 1e-4 fp16=True as shown in the figure, there are periodic, sudden drops in losses,...

ubuntu无法使用ctrl + 滚轮缩放图片

6

在Ubuntu上通过源码启动软件，操作的时候遇到几个问题想请教一下： 1. 通过ctrl + 滚轮无法缩放图片，但是我看手册里面有写到，不确定是什么问题？ 2. 如何添加两个子文件夹进行对比？Parallel manual只能通过设定子文件夹的方式来进行 希望能够增加更加方便、自由的文件夹、图片对比方式

when visualizing the feature center, why use the first and the second dimension of the feature as x and y? 

At the beginning of training, the center loss is very large, for example, 520, although the use of pre-trained model. PS. I use the arcface as pre-train before adding center...