ChenFengYe/motion-latent-diffusion

Issues

• Problem on T2M Evaluation with New Dataset

  #61 opened 2 months ago by voidffu
  1

• t2m checkpoint model size error

  #26 opened 2 years ago by yhyu13
  4

• Could you please make all the files related to the KIT dataset publicly available?

  #62 opened a month ago by wjxxyz
  0

• A problem about VAE

  #59 opened 3 months ago by Terry-Joy
  7

• Best Model Selection During Training

  #60 opened 3 months ago by Zhongan-Wang
  0

• Pre-trained VAE weights

  #58 opened 4 months ago by gentlefress
  1

• I got the error form demo.py

  #42 opened a year ago by Theweekfoolish229
  1

• Why not using VQVAE like stable diffusion?

  #40 opened a year ago by daidaiershidi
  11

• Training configuration on KIT dataset

  #13 opened 2 years ago by Dean-UQ
  8

• SkipTransformer and None Skip Transformer

  #54 opened a year ago by ZenGengChin
  1

• How many epochs do you train on your VAE？

  #57 opened 7 months ago by feifeitu1
  0

• How did you get the word embeddings of size (B,300) in our_vab_data.npy?

  #56 opened 7 months ago by kaustesseract
  0

• Error with "name_list" and "length_list" in datasets

  #53 opened a year ago by alsokh
  7

• Result of novae model

  #47 opened a year ago by hoyeYang
  6

• Visualize SMPL

  #14 opened 2 years ago by wang-zm18
  3

• Render SMPL meshes

  #51 opened a year ago by exitudio
  2

• Results Stage1 KIT Dataset

  #50 opened a year ago by AlessioSam
  3

• How to use the a2m models/config?

  #55 opened a year ago by ou524u
  0

• VAE training for FID=0.017

  #52 opened a year ago by ZenGengChin
  1

• About MultiModality and Matching Score

  #49 opened a year ago by fyyakaxyy
  0

• According to Figure 2, the VAE stage does not use any text input?

  #45 opened a year ago by layumi
  0

• About the prior in mld.py and memory in mld_denoiser

  #48 opened a year ago by 1994cxy
  2

• Motion Representations

  #41 opened a year ago by cyk990422
  2

• Reproducing KIT results

  #44 opened a year ago by nefeliandreou
  0

• how to change the length of the motion?

  #36 opened a year ago by ShungJhon
  3

• Hand + Face of Human Pose

  #46 opened a year ago by p0mad
  0

• Where is action-to-motion code?

  #43 opened a year ago by xwg0508
  0

• Can you provide instructions for other datasets such as UESTC and HumanAct12?

  #39 opened a year ago by Xuguowei-hub
  2

• Mask on clips with varied length

  #38 opened a year ago by csvt32745
  2

• How to evaluate action-to-motion task on UESTC and HumanAct12 datasets？

  #37 opened 2 years ago by maweizhao
  0

• how to use the trained model ckpt for test?

  #35 opened 2 years ago by ShungJhon
  2

• how can i get a long sequences

  #34 opened 2 years ago by zhLawliet
  0

• About performance

  #33 opened 2 years ago by layumi
  2

• Is this result as expected?

  #31 opened 2 years ago by zhLawliet
  2

• how can i use smpl rot6d motion_representation for motion reconstruct

  #30 opened 2 years ago by jihg88
  2

• Unable to run demo.py without HumanML3D dataset

  #23 opened 2 years ago by lzyplayer
  5

• Question about generating result jitter

  #29 opened 2 years ago by cyk990422
  4

• About the encode part of VAE

  #28 opened 2 years ago by FortisCK
  1

• I have obtained R-precision test results, but they differ from those reported in the paper.

  #27 opened 2 years ago by gaogehan
  4

• Pretrained VAE model

  #25 opened 2 years ago by chinnusai25
  0

• Issue with pytorch lightning

  #24 opened 2 years ago by chinnusai25
  1

• VAE testing result

  #22 opened 2 years ago by borishanzju
  5

• ValueError: Expected parameter loc (Tensor of shape (1, 64, 256)) of distribution Normal(loc: torch.Size([1, 64, 256]), scale: torch.Size([1, 64, 256])) to satisfy the constraint Real()

  #21 opened 2 years ago by borishanzju
  0

• Question about training on humanml3d dataset

  #20 opened 2 years ago by HoBeom
  2

• The version of pytorch_lightning

  #19 opened 2 years ago by qiqiApink
  1

• How to verify whether the training of VAE is good?

  #16 opened 2 years ago by LinghaoChan
  5

• KL loss function

  #18 opened 2 years ago by Ying156209
  1

• VAE random generation

  #17 opened 2 years ago by Ying156209
  1

• Exporting motions to bvh

  #15 opened 2 years ago by aplatyps
  3

• Visualization and understanding of latent space

  #12 opened 2 years ago by ChenFengYe
  5