wilson1yan/VideoGPT

Issues

• i3d loading error

  #44 opened 3 months ago by rook86
  0

• VQ-VAE VQ-loss is missing? only find reconstruct, and commitment loss

  #39 opened a year ago by yiqiwang8177
  1

• How to predict next frames using one frame

  #40 opened a year ago by Mu-Yanchen
  2

• Tensor Size Mismatch in attention.py

  #28 opened 7 months ago by humishum
  3

• The Torch version is a problem when running in Colab.

  #38 opened 7 months ago by LuthandoMaqondo
  1

• Moving MNIST code?

  #41 opened 8 months ago by V0XNIHILI
  0

• How many frames (seconds) are there in each video sample used in the training process?

  #34 opened 2 years ago by BinZhu-ece
  4

• Could this be used as a next frame predictor?

  #16 opened 3 years ago by radi-cho
  10

• unknown error

  #35 opened 2 years ago by BoccheseGiacomo
  8

• Next frame predictor

  #37 opened 2 years ago by Piyush-555
  0

• Questions about downsample and codebook

  #36 opened 2 years ago by qklee-lz
  0

• deepspeed version

  #33 opened 2 years ago by yrcong
  2

• Caching during sampling without effect in cross-attention?

  #32 opened 2 years ago by Natithan
  1

• Getting "UnpicklingError: invalid load key, '<'." while downloadfing pretrained weights

  #30 opened 3 years ago by Chetan-O6
  2

• Running on 4 V100s, but epoch stays at 0

  #23 opened 3 years ago by slerman12
  6

• Extending your code for poses

  #29 opened 3 years ago by AmitMY
  1

• Issues about the python version

  #27 opened 3 years ago by baiyuting
  3

• Issue with memory only with your code

  #25 opened 3 years ago by Scienceseb
  1

• the previous dependency is only one time step during inference?

  #24 opened 3 years ago by PanXiebit
  2

• vqvae finetuning procedures

  #8 opened 3 years ago by Goulustis
  4

• Generating longer sequences

  #22 opened 3 years ago by universome
  6

• Video retrival

  #4 opened 3 years ago by Tortoise17
  1

• Some questions on VideoGPT.

  #17 opened 3 years ago by kami93
  4

• video formatting

  #21 opened 3 years ago by a-antoniades
  2

• setting attribute

  #20 opened 3 years ago by a-antoniades
  2

• AssertionError: Must set max_steps argument

  #19 opened 3 years ago by slerman12
  2

• Question about data dependent initialization

  #18 opened 3 years ago by sukun1045
  3

• FVD score not conform to what's reported in the paper

  #15 opened 3 years ago by Gabriel-Huang
  5

• DeepSpeed numeric issue with FP32

  #14 opened 3 years ago by songweige
  2

• Should we train the prior model with n_cond_frames>=1 for BAIR Pushing dataset?

  #12 opened 3 years ago by xinbowu2
  1

• Number of Layers for Prior Model

  #11 opened 3 years ago by xinbowu2
  4

• shiftdim instead of torch.movedim

  #13 opened 3 years ago by FrancoisPgm
  1

• hdf5 file for bair robot dataset

  #9 opened 3 years ago by Gabriel-Huang
  2

• transformer training details

  #7 opened 3 years ago by Goulustis
  1

• Compute compatibility?

  #6 opened 3 years ago by slerman12
  6

• Downloading UCF-101 data error

  #5 opened 3 years ago by slerman12
  1

• scripts/sample_videogpt.py is missing?

  #3 opened 3 years ago by josephrocca
  2

• Is there something wrong with the online demo?

  #2 opened 3 years ago by lastapple
  3