-
## Detailed description
我看论文中在lateral connections中采用的是1X1卷积,但是看代码中实现的是3X3 kernel大小。是否这样实现的性能更高，就是单纯的求问一下哈
> Then at each stage, a 1 × 1 convolutional layer is taken to rearrange the features and ad…
-
Only the performance of the CASIA-B gait dataset is put up on the arxiv version of your paper. In the ./src/common.py, the choices for '--dataset' are ["casia-b", "outdoor-gait", "tum-gaid"]. Would yo…
-
Hello, when I installed, there was a grammatical error, could you help me to check it? Thank you !
(dan_3.6) x1234@hbuzntw002-Precision-7920-Tower:~/Dan/Dan_Project$ python setup.py install
[LIBJP…
-
Hello!
Thanks for your inspiring work. And I 'm very intersted in it.
Last two weeks, I read your great work and decided to re-Implement your network according to the paper.
However, after two week…
-
Hi:
I have a question that needs your help.Thanks
File "/data6/liangjie/project/AdvFaces-master/utils/dataset.py", line 106, in init_from_path
It should be either a folder, .txt or .hdf5 file'…
-
Hi there again!
I got an error when initiating the training, it gives me this output.
![image](https://user-images.githubusercontent.com/77947380/135193319-9165d92f-14c2-4595-9d0a-5b00833ed1ce.png…
-
Hello, I use the "CASIA2.0" training mentioned in the paper, and the problems in the picture below always appear.
But I trained with my own data set and I could train normally but poorly.
In additio…
-
Hello, I am a Msc student and I am developing a zero-shot learning solution to the face spoofing problem. I am trying to incorporate a rPPG component. I have tried to use a code similar to the one on …
-
Hello!
Thank you very much for releasing the code.
My question is What should I fill in line7/8 of train.sh.
train_lmdb='path to your training lmdb, it is comma separated'
train_fil…
-
I am trying to reimplement your paper and I'm having problems with convergence. In the paper is said you used lr=5e-3 and SGD optimizer for 50 epochs. Did you change the learning rate after 50 epochs…