yuangan/EAT_code

Issues

• How long does it take to train?

  #41 opened 3 months ago by Sprinkle0
  1

• sync loss error

  #40 opened 4 months ago by StephanPan
  0

• 关于Vox数据集的预处理

  #19 opened 10 months ago by YZX-codesky
  14

• Can anyone share TED-Talk dataset？

  #39 opened 4 months ago by zouzhekang
  0

• Fail to get output from demo.py

  #38 opened 5 months ago by andysummer0715
  2

• Inquiry Regarding Preprocessing VOX2 and MEAD Dataset for Training

  #37 opened 5 months ago by Calmepro777
  8

• mead数据压缩问题

  #36 opened 5 months ago by bronzeman2022
  1

• 关于预训练使用的权重

  #35 opened 5 months ago by Mhq-we
  3

• Error in saving .npy file

  #33 opened 5 months ago by subharya83
  2

• Inquiry Source Data Preparation

  #32 opened 6 months ago by Calmepro777
  2

• How to generate files for custom audio?

  #34 opened 6 months ago by subharya83
  4

• FileNotFoundError: Package has no location <module 'imageio_ffmpeg.binaries' (namespace)>

  #31 opened 6 months ago by Mariosz2
  2

• Details about CLIP fine-tuning and zero-shot text-guided editing

  #30 opened 7 months ago by JamesLong199
  11

• How to edit with text and interpolate states as described in the paper?

  #23 opened 9 months ago by G-force78
  2

• 3D Keypoint Enhancement Training

  #29 opened 7 months ago by JamesLong199
  2

• Any way support for Chinese audio?

  #28 opened 7 months ago by lililuya
  3

• 请问如果只有图片+语音，没有 pose 如何推理

  #16 opened a year ago by Wangman1
  12

• Generated Video Background Is Not Static

  #27 opened 7 months ago by hrWong
  3

• ValueError: setting an array element with a sequence. The requested array has an inhomogeneous shape after 1 dimensions. The detected shape was (2,) + inhomogeneous part.

  #26 opened 8 months ago by lililuya
  2

• No discriminator in the state-dict. Dicriminator will be randomly initialized load optimizer_a2kp failed, train it from scratch

  #25 opened 8 months ago by YZX-codesky
  5

• Would it be complicated to add eyeblinking reference videos?

  #24 opened 8 months ago by G-force78
  1

• 关于训练收敛的问题

  #22 opened 9 months ago by YZX-codesky
  3

• RuntimeError: The size of tensor a (165) must match the size of tensor b (66) at non-singleton dimension 1 on my training dataset

  #20 opened 9 months ago by Yazdi9
  1

• nothing happens when I run demo.py

  #10 opened a year ago by G-force78
  11

• AssertionError: Caught AssertionError in DataLoader worker process 0.

  #21 opened 9 months ago by Yazdi9
  2

• Dimension not matching when training Emotional Adaption

  #18 opened 10 months ago by phphuc612
  1

• MEAD test list

  #17 opened 10 months ago by chaolongy
  1

• 训练时间

  #15 opened a year ago by YZX-codesky
  3

• The training code

  #7 opened a year ago by julia-cherry
  7

• 关于voxs_images和voxs_wavs

  #14 opened a year ago by Tpcsy
  2

• 请问所有的代码都已经开源了吗

  #13 opened a year ago by Wangman1
  1

• How to change a new image as input?

  #12 opened a year ago by piwawa
  1

• 能否提供“评价指标”的量化代码

  #11 opened a year ago by laura990501
  1

• How can I replace the wav?

  #6 opened a year ago by skeletonNN
  5

• Error when running preprocess.py No module named resamply

  #9 opened a year ago by G-force78
  6

• Custom Video - Preprocess code

  #3 opened a year ago by oijoijcoiejoijce
  4

• About training code

  #4 opened a year ago by HJHGJGHHG
  1

• About animating an image

  #2 opened a year ago by chenerg
  3

• where is the paper?

  #1 opened a year ago by tanshuai0219
  3