xinwen-cs/AudioDVP

Issues

• Error from nvcc

  #43 opened 6 months ago by sharikian
  0

• Wondering about the scale factor used in build_data script

  #42 opened 7 months ago by Wecombo
  1

• Pretrained model missing

  #41 opened 8 months ago by ZXisSpider
  1

• 关于delta 的具体含义？

  #35 opened 3 years ago by DWCTOD
  1

• rasterize_triangles_cpp not found even after step 6.

  #21 opened 4 years ago by mrlatnek
  1

• 本地Tesla V100推理时间和论文GTX 2080 ti进行推理的时间相差太大

  #29 opened 3 years ago by iamchenxin-coder
  5

• delta_net.pth

  #38 opened a year ago by Winfredy
  1

• 您好！请问我训练完成后，该使用哪些代码进行推理呢？还望指教

  #39 opened a year ago by 572120986
  0

• The actual test results of others are different from those in the paper

  #40 opened a year ago by Arthurzhangsheng
  1

• 黑点

  #34 opened 3 years ago by 425776024
  2

• 关于Audio2expression模型相关求助

  #31 opened 3 years ago by 821029883
  2

• When I go to the "dataset [singledataset] was created" step，Something went wrong

  #37 opened 3 years ago by supersarr
  3

• .

  #36 opened 3 years ago by zg734
  0

• RuntimeError: triangles.is_contiguous() INTERNAL ASSERT FAILED at "rasterize_triangles.cpp"

  #23 opened 3 years ago by iamchenxin-coder
  4

• Could you provide where to download data used for the paper?

  #22 opened 3 years ago by grey10170
  1

• train_exp.py运行出错

  #24 opened 3 years ago by iamchenxin-coder
  0

• run reenact.py error

  #25 opened 3 years ago by iamchenxin-coder
  1

• 训练神经网络人脸渲染器会在某个epoch卡死

  #28 opened 3 years ago by RylanLiu-buaa
  1

• 论文中没有提到输入测试音频的采样率和目标视频的采样率必须一致

  #30 opened 3 years ago by iamchenxin-coder
  1

• 如何训练中文数据集？

  #32 opened 3 years ago by Adorablepet
  3

• ImportError: libtorch_cpu.so: cannot open shared object file

  #26 opened 3 years ago by yddr
  0

• OMP: Error #13: Assertion failure at z_Linux_util.cpp(2338).

  #27 opened 4 years ago by mrlatnek
  0

• Thanks your work. how to obtain full model that includes ear and neck.

  #19 opened 4 years ago by rui-mian-wen
  1

• how to adjust landmarks?

  #20 opened 4 years ago by zhouquan9
  1

• how to increase the size of output video ?

  #15 opened 4 years ago
  7

• why the mask is bigger?

  #18 opened 4 years ago
  1

• why the people not in the center of the picture ?

  #16 opened 4 years ago
  1

• ./scripts/demo.sh: 行 104: 30820 已杀死 会爆内存

  #17 opened 4 years ago
  2

• how to train with chinese?

  #14 opened 4 years ago
  4

• triangles must be contiguous

  #12 opened 4 years ago
  3

• loss is right?

  #13 opened 4 years ago
  1

• RuntimeError: triangles.is_contiguous() INTERNAL ASSERT FAILED ,can u give some ad

  #9 opened 4 years ago by anthonyyuan
  3

• pretrained model

  #11 opened 4 years ago by chensheng-code
  2

• Step: Crop and resize video frames too slow

  #7 opened 4 years ago by House-Leo
  6

• no delta_net.pth

  #10 opened 4 years ago by luoww1992
  1

• hi

  #8 opened 4 years ago by anthonyyuan
  1

• colab

  #5 opened 4 years ago by ak9250
  1

• Could not find the rasterize_triangles_cpp

  #6 opened 4 years ago by doctorimage
  2

• ./scripts/merge_frames.sh not found

  #4 opened 4 years ago by qianxinchun
  2

• can not find 'python_speech_features' module

  #3 opened 4 years ago by eudoraxj
  1

• Can't find expression basis

  #2 opened 4 years ago by qianyunw
  6

• Error while setup.py build_ext

  #1 opened 4 years ago by shillerz
  1