LuoweiZhou/VLP

Issues

• Regarding data count mismatch in Flickr30k dataset annotations' json file?

  #48 opened 4 months ago by Jayashree-Pougajendy
  0

• Google Drive Link for 509G Feat Invalid, Please Help With An Alternate Download Link

  #47 opened 8 months ago by varungupta31
  0

• About pre-computed image features

  #46 opened 3 years ago by peterLeeeee
  0

• Data Download Problem

  #33 opened 4 years ago by tjuwyh
  29

• Change N object of feature extractor and number of attention head

  #45 opened 3 years ago by khiemledev
  0

• region geometric information

  #44 opened 3 years ago by xiaohu306
  1

• the JSON file of dataset is in need

  #43 opened 3 years ago by Hepta-Col
  0

• Could you plz tell me how to use the pre-trained model to perform image caption on coco dataset?

  #42 opened 3 years ago by meiling-fdu
  3

• Is it possible to inference the caption of one image without downloading the whole training dataset?

  #29 opened 4 years ago by xden2331
  3

• Other Pretrained Models

  #41 opened 4 years ago by jingjingdd
  2

• Train model when I have image only without any bbox info

  #39 opened 4 years ago by Decalogue
  1

• Bus error (core dump) during training

  #40 opened 4 years ago by ChenYutongTHU
  1

• Can't reproduce the scst results

  #38 opened 4 years ago by Leoncatd
  3

• Getting `No module named 'apex.optimizers'` error

  #36 opened 4 years ago by gsrivas4
  5

• error: command 'gcc' failed with exit status 1 raised in installing apex

  #37 opened 4 years ago by ChenYutongTHU
  0

• Not able to load pre-trained model on CC dataset

  #35 opened 4 years ago by chenyez
  2

• Dimension of Position Embedding

  #34 opened 4 years ago by HollowFire
  1

• segment core while running evaluation

  #32 opened 4 years ago by TangDonnie
  2

• Pretrained Model

  #24 opened 4 years ago by mitjanikolaus
  6

• Some missing *_cls_prob.npy files in Flickr30k

  #31 opened 4 years ago by shrutijpalaskar
  2

• Require a quick start for simple usage...

  #30 opened 4 years ago by wubowen416
  7

• unable to Download feature from google drive

  #28 opened 4 years ago by youngfly11
  3

• Possibility of bugs when not enable butd - decode_img2txt.py and seq2seq_loader.py

  #27 opened 4 years ago by windspirit95
  1

• UnboundLocalError: local variable 'vis_pe' referenced before assignment

  #26 opened 4 years ago by curehabit
  1

• Bert Model

  #25 opened 4 years ago by kemalaraz
  3

• Finetuning and Testing on separate dataset

  #23 opened 4 years ago by nikky4D
  2

• Optimizer state dict for RL fine-tuning

  #22 opened 4 years ago by aleSuglia
  1

• coco-caption commit is orphaned and can no longer be checked out

  #21 opened 5 years ago by kracwarlock
  1

• Finetuning checkpoints link not working

  #20 opened 5 years ago by yjxiao
  2

• MSCOCO data not found

  #19 opened 5 years ago by xinyuwang1126
  3

• adding specific tokens to vocabulary

  #18 opened 5 years ago by xinyuwang1126
  2

• Chinese image caption， In the result, multiple words of the same type appear

  #17 opened 5 years ago by cylvzj
  5

• What is GPU memory size of your V100? (ERROR: Unexpected bus error encountered in worker)

  #5 opened 5 years ago by yuewang-cuhk
  10

• UniLM checkpoint is no longer available

  #16 opened 5 years ago by GabrielLin
  5

• why the dimenson of region object labels is 1601?

  #15 opened 5 years ago by Leoncatd
  2

• When will you release the visual feature detectron code?

  #9 opened 5 years ago by yuewang-cuhk
  7

• Unable to reproduce image features for COCO and CC

  #12 opened 5 years ago by darkmatter08
  8

• Invalid UniLM checkpoints

  #14 opened 5 years ago by lostnighter
  1

• File Not Found：feat_cls_1000_float16/cc_detection_vg_100dets_gvd_checkpoint_trainval

  #13 opened 5 years ago by zhao1iang
  4

• Question about seq2seq decoder generation

  #10 opened 5 years ago by aleSuglia
  1

• Values in Region Geometric Information

  #11 opened 5 years ago by Ago3
  2

• Performance improvements for data loading process

  #4 opened 5 years ago by aleSuglia
  2

• Detectron feature extraction

  #7 opened 5 years ago by leotam
  8

• [BUG]: AttributeError: 'Tensor' object has no attribute 'append'

  #8 opened 5 years ago by aleSuglia
  3

• Multiple GPUs Support

  #3 opened 5 years ago by idansc
  6

• The repo is back on!

  #1 opened 5 years ago by LuoweiZhou
  0