ZcyMonkey/AttT2M

Issues

• fid is bigger than 80, unable to get the result you provided using checkpoints/pretrained_models/humanml3d/vqvae/net_last.pth

  #7 opened 3 months ago
  0

• Attention matrix shape

  #6 opened 4 months ago
  1

• About the word_emb for cross attention

  #5 opened 5 months ago
  0

• Visualization of Motion-word cross-attention

  #4 opened 7 months ago
  1

• can't find net_best_fid.pth

  #3 opened 7 months ago
  3

• Question on the VQVAE spatial encoder design

  #2 opened 9 months ago
  1

• Code update

  #1 opened a year ago
  1