google-research/slot-attention-video

Issues

• The Waymo cfg file and processing code

  #7 opened 2 years ago by ruili3
  5

• Out of Memory (OOM) error when running the code

  #21 opened a year ago by rgiraud
  1

• The request for TPU training model

  #20 opened a year ago by K-lina
  0

• Slot attention vs Transformer

  #19 opened a year ago by MLDeS
  0

• Is there a Pytorch version available?

  #1 opened 2 years ago by iamtonymwt
  3

• Difference between MOVI-A and MOVI

  #18 opened a year ago by hnyu
  4

• Unconditional setting does not yield reasonable results on the challenging MOVi-E

  #12 opened 2 years ago by ruili3
  2

• Original error: UNIMPLEMENTED: DNN library is not found.

  #17 opened a year ago by XinyangHan
  0

• SAVi++ conditional background

  #16 opened a year ago by Divadi
  1

• The sequence iteration part was not found

  #15 opened a year ago by wangjiannb
  0

• It seems that num_heads for SlotAttention is 1?

  #13 opened 2 years ago by wcarvalho
  2

• Sub-optimal results on customized KITTI dataset

  #14 opened 2 years ago by ruili3
  3

• Skipping first frame in eval?

  #10 opened 2 years ago by mseitzer
  1

• Difference between results (of MOVi C/D/E ) reported in the paper and in the github post

  #8 opened 2 years ago by ruili3
  2

• Could you provide the unconditional cfg for CATER dataset?

  #6 opened 2 years ago by rayeeli
  2

• Implementation details for CATER dataset

  #11 opened 2 years ago by a-imamshah
  1

• Encoder in SAVi++ configuration

  #9 opened 2 years ago by mseitzer
  0

• Could you please provide model config file when using segmentation as conditioning?

  #5 opened 2 years ago by YRlin-12
  1

• Warning from clu.metrics when running evaluation

  #4 opened 2 years ago by YingtianDt
  6

• Reimplemtation and Model Architecture issues

  #3 opened 2 years ago by junkeun-yi
  1

• requirements.txt installs packages that are too new and do not work

  #2 opened 2 years ago by simo-tuomisto
  1