simon-ging/coot-videotext

Issues

• Can I add your loss function to my non-Transformer model?

  #56 opened 8 months ago by Wangdanchunbufuz
  3

• Running the code for videos

  #55 opened a year ago by ShaadAkhtar
  1

• inference

  #54 opened 2 years ago by LilyTheBear
  1

• Complete example of captioning a video

  #53 opened 2 years ago by Hussam-Turjman
  0

• Video 100m feature extraction

  #17 opened 4 years ago by mireiahernandez
  8

• Using the model to predict video caption

  #50 opened 3 years ago by YoussefZiad
  4

• How can I save checkpoint?

  #52 opened 2 years ago by teang1995
  1

• Feature representations for external videos

  #51 opened 2 years ago by arelhossan
  1

• Cannot Reproduce Result on paper

  #49 opened 3 years ago by teang1995
  1

• What is Youcook2 with Howto100m features Procedure?

  #46 opened 3 years ago by Maddy12
  1

• Num Frames json

  #48 opened 3 years ago by Maddy12
  1

• Transformers older version failling, hack included

  #47 opened 3 years ago by Maddy12
  2

• How can I use this model to make video caption for a raw dataset

  #45 opened 3 years ago by Karshilov
  2

• How do you look at retrieved text data?

  #44 opened 3 years ago by mtsandmeyer
  1

• How can i reproduce the performance in the paper?

  #43 opened 3 years ago by Anikily
  1

• NAN error when training the TransformerXL model on yc2 dataset

  #42 opened 3 years ago by robert1015
  1

• [BUG]

  #41 opened 3 years ago by GX77
  3

• How can I extract the COOT features for my chinese caption datasets？

  #40 opened 3 years ago by will-wiki
  4

• PackagesNotFoundError: package version with 'torchaudio==0.7.0a0+a853dff'

  #39 opened 3 years ago by teddy309
  1

• PackagesNotFoundError: torchaudio==0.7.0a0+a853dff

  #38 opened 3 years ago by YOONSEOKHEO
  0

• FileNotFoundError: [Errno 2] No such file or directory: 'data/youcook2/meta_all.json'

  #37 opened 3 years ago by code10086web
  1

• Coot features for a new dataset

  #20 opened 3 years ago by medhini
  4

• how can i get a h5 like this "provided_embeddings/yc2_100m_coot_val.h5"

  #36 opened 3 years ago by yuhao910716
  1

• Can't download the Prepare pretrained models / embeddings

  #30 opened 3 years ago by gaoliming123
  1

• visualization of results

  #35 opened 4 years ago by liujiaqiKiKi
  7

• Run:python train_caption.py -c config/caption/paper2020/yc2_100m_coot_vidclip_mart.yaml[BUG]

  #33 opened 4 years ago by liujiaqiKiKi
  9

• Fine tune yc2_100m_coot_vidclip_mart for smaller videos

  #34 opened 4 years ago by DesaleF
  5

• Get error when train TransformerXL on COOT embeddings

  #32 opened 4 years ago by menggehe
  2

• Have you tried using 'mixed_5c' as frame embeddings for howto100m model?

  #31 opened 4 years ago by andylin12
  2

• [BUG] multi gpu training without --single_gpu

  #19 opened 4 years ago by menatallh
  6

• Does COOT uses ground truth timestamp to generate coherent caption(Paragraph)?

  #28 opened 4 years ago by DesaleF
  4

• Does the pretrained model work for Chinese?

  #21 opened 4 years ago by PipiZong
  1

• python data_read_youcook2_meta.py where youcook2/meta_all.json?

  #27 opened 4 years ago by jun0wanan
  2

• Get error on Train and validate MART on COOT embeddings

  #23 opened 4 years ago by DesaleF
  5

• why random sample during training and center sample during validation?

  #25 opened 4 years ago by menggehe
  2

• Is there any Google collab notebook available?

  #22 opened 4 years ago by harshraj32
  1

• Run:python3 train_retrieval.py -c config/retrieval/paper2020/anet_coot.yaml

  #14 opened 4 years ago by haoshuai714
  8

• Backwards compatibility for PyTorch 1.4

  #18 opened 4 years ago by lzlzlizi
  7

• No module named 'mart'

  #16 opened 4 years ago by ericwang0701
  2

• Have you tried pre-trained features on ActivityNet?

  #8 opened 4 years ago by PKULiuHui
  4

• About the video captioning

  #4 opened 4 years ago by PKULiuHui
  8

• Video captioning code release

  #11 opened 4 years ago by PipiZong
  7

• Provided Embeddings File Missing

  #15 opened 4 years ago by ShaSha146
  1

• [BUG] CMC loss in the master

  #12 opened 4 years ago by lzlzlizi
  3

• Can you provide a Baidu cloud disk database download link?

  #2 opened 4 years ago by haoshuai714
  3

• Train from scratch

  #10 opened 4 years ago by haoshuai714
  6

• FileNotFoundError: [Errno 2] No such file or directory: 'data/activitynet/captions/train.json'

  #7 opened 4 years ago by haoshuai714
  1

• The link to download activitynet-caption features seems broken, could you please check it?

  #1 opened 4 years ago by chenchengfd
  5

• where is youcookii_annotations_trainval.json

  #3 opened 4 years ago by lzlzlizi
  2

• About `TransformerEncoder`

  #5 opened 4 years ago by lzlzlizi
  2