uclanlp/visualbert

Issues

• How to retrain VisualBERT on another dataset?

  #46 opened 6 months ago by Tess314
  0

• Visualbert VQA model inference lower accuracy in validation around 40% by huggingface framework

  #45 opened a year ago by guanhdrmq
  0

• Minimum GPU requirement

  #44 opened a year ago by nowhash
  0

• Not able to download NLVR train feature file

  #41 opened 2 years ago by shantanuhumbe
  0

• ModuleNotFoundError: No module named 'visualbert'

  #39 opened 2 years ago by F-Yuan303
  0

• VisualBERT with Detectron2

  #38 opened 2 years ago by smfsamir
  0

• How to get pre-computed features in NLVR2 task for my own dataset?

  #37 opened 2 years ago by bigbrother001
  0

• Extracting image features for VQA

  #10 opened 4 years ago by johntiger1
  6

• Extracting Detectron Features

  #1 opened 5 years ago by sanjayss34
  8

• COCO features

  #22 opened 4 years ago by qinzzz
  2

• missing COCO Pre-training checkpoint in Flickr30K

  #36 opened 3 years ago by mingfengwuye
  0

• allennlp 0.8.0 .

  #20 opened 4 years ago by alice-cool
  7

• checkpoints for flickr30k?

  #35 opened 3 years ago by ziyanyang
  0

• How to use visualbert for visual grounding(entity grounding)?

  #34 opened 3 years ago by gagaein
  0

• about chinese

  #32 opened 3 years ago by Soulscb
  1

• Features vqacoco-pre-train

  #31 opened 3 years ago by RitaRamo
  1

• Bert-large

  #27 opened 3 years ago by 1144181135
  1

• Contact author

  #33 opened 3 years ago by zxy-in
  0

• About evaluation

  #30 opened 3 years ago by renmada
  1

• Process finished with exit code 137

  #29 opened 3 years ago by lifebl
  0

• How to make evaluation on VQA?

  #5 opened 4 years ago by yangapku
  1

• The ROIAlign module used in VCR experiments crushes when forwarding

  #4 opened 4 years ago by yangapku
  4

• Flickr30k entities support

  #6 opened 4 years ago by fbrad
  1

• about MCAN

  #19 opened 4 years ago by ckj1221
  1

• sentence image matching

  #21 opened 4 years ago by goodbai2
  1

• Visual Features Computation

  #24 opened 4 years ago by michelecafagna26
  1

• seq_relationship_score logits order

  #26 opened 4 years ago by michelecafagna26
  1

• Question about visualBERT

  #8 opened 4 years ago by YuBeomGon
  1

• ModuleNotFoundError: No module named 'visualbert'

  #18 opened 4 years ago by michelecafagna26
  1

• COCO pre-training size

  #17 opened 4 years ago by e-bug
  1

• 有大佬开源个Keras版本的吗？

  #23 opened 4 years ago by fengxin619
  0

• How to Generate Visual Attention Maps

  #16 opened 4 years ago by g-luo
  1

• "VisualBERTDetector not in acceptable choices for type

  #15 opened 4 years ago by menggehe
  1

• Using visualBERT for generation

  #14 opened 4 years ago by nishanthcgit
  2

• Pre-training on other BERT models

  #12 opened 4 years ago by Muennighoff
  2

• Number of ROIs

  #11 opened 4 years ago by e-bug
  1

• Mask Probabilty for Task-specific Pre-training

  #13 opened 4 years ago by Muennighoff
  2

• Flickr30k Entities fine-tuning clarification

  #9 opened 5 years ago by tonyduan
  2

• "pre-training" section in the readme

  #7 opened 5 years ago by johntiger1
  1

• config_vcr is no where to be found

  #3 opened 5 years ago by ChenghaoMou
  2