jackroos/VL-BERT

Issues

• fine-tune

  #70 opened 4 years ago by cxjtju
  1

• How to pretrain on my own data?

  #74 opened 4 years ago by xealml
  2

• An example for image feature

  #75 opened 4 years ago by changjiangamy
  3

• RuntimeError: Not compiled with GPU support (ROIAlign_forward at

  #58 opened 4 years ago by menggehe
  1

• script for downloading GCC images

  #88 opened 2 years ago by sesmae
  0

• subprocess.CalledProcessError: Command xxx returned non-zero exit status 1.

  #41 opened 4 years ago by gm0616
  3

• Could only download 400k images

  #54 opened 4 years ago by gsrivas4
  5

• google drive

  #86 opened 3 years ago by zhangdabusy
  0

• Why cannot import name 'C_ROIPooling' from 'common.lib.roi_pooling'

  #59 opened 4 years ago by wenhao7841
  5

• Is the refcoco-trained model available?

  #67 opened 4 years ago by st2yang
  5

• Is the nvcc necessary?

  #85 opened 3 years ago by TomatoShitOne
  0

• How to freeze the Fast RCNN?

  #84 opened 3 years ago by KKK12321
  0

• Improper RefCOCO evaluation

  #83 opened 3 years ago by st2yang
  0

• Can I get the object label ?

  #82 opened 3 years ago by PamelaDDD
  0

• CUDA error: no kernel image is available for execution on the device

  #81 opened 3 years ago by nikhilbchilwant
  0

• Pretrained VL-BERT model on bert_based_multilingual_uncased needed to apply zero shot learning for German language

  #80 opened 4 years ago by aggarwalpiush
  0

• Caffe feature extraction for conceptual-captions - where do I make pycaffe?

  #79 opened 4 years ago by yonatanbitton
  0

• Is there an option to upload the the val_frcnn features?

  #78 opened 4 years ago by yonatanbitton
  0

• Obtaining visual features for the ConceptualCaptions data set

  #50 opened 4 years ago by jules-samaran
  2

• Why the preprocessing method differs from the official method of pytorch

  #77 opened 4 years ago by vanpersie32
  0

• Does the pre-trained BERT come from vl-bert ?

  #76 opened 4 years ago by zzy994491827
  1

• fatal error: torch/extension.h: No such file or directory

  #64 opened 4 years ago by whqwill
  2

• what is text_visual_embeddings

  #73 opened 4 years ago by xugy16
  0

• CUDA Illegal Memory Access In FastRCNN with ROIAlign

  #72 opened 4 years ago by tkreiman
  0

• visualize attention for custom images

  #71 opened 4 years ago by betterze
  0

• ./scripts/init.sh

  #69 opened 4 years ago by alice-cool
  4

• The problem of multitasking parallel processing

  #68 opened 4 years ago by Pter61
  4

• Unrecognized tensor type ID: AutogradCUDA

  #61 opened 4 years ago by jkkishore1999
  6

• Questions about faster-rcnn

  #66 opened 4 years ago by Pter61
  0

• What is the meaning of MVRC_LOSS? What use is it？

  #63 opened 4 years ago by Pter61
  1

• type_vocab_size of pretrained model should be 2

  #65 opened 4 years ago by whqwill
  1

• Can the VL-BERT model be applied to metric learning?

  #62 opened 4 years ago by zhoulukuan
  3

• How is vgbua_res101_precomputed generated?

  #57 opened 4 years ago by lmd1993
  1

• RuntimeError：CUDA out of memory

  #49 opened 4 years ago by liulijie-2020
  2

• cuda version

  #43 opened 4 years ago by campper
  15

• Working with CUDA 10.1

  #42 opened 4 years ago by clairecyq
  1

• segmentation fault

  #60 opened 4 years ago by annazare
  0

• subprocess.CalledProcessError: Command xxx returned non-zero exit status 1

  #47 opened 4 years ago by jaeyun95
  4

• 为何只训练coco2014的一张图片时出错，但训练全部的图片不报错？

  #56 opened 4 years ago by nyj-ocean
  0

• __init__() missing 2 required positional arguments: 'doc' and 'pos'

  #53 opened 4 years ago by tqace
  3

• GCC version

  #52 opened 4 years ago by titaiwangms
  2

• Is the roialign part forgotten compiled ?

  #51 opened 4 years ago by Liu0329
  3

• Doesn't it offer a fine-tuned VCR model?

  #48 opened 4 years ago by jaeyun95
  2

• THCudaCheck FAIL

  #46 opened 4 years ago by tejas1995
  2

• Hyperparameters mismatch

  #40 opened 4 years ago by e-bug
  1

• _pickle.UnpicklingError: invalid load key, '-'.

  #45 opened 4 years ago by liulijie-2020
  7

• some question about the codes in ./common/faster_rcnn.py

  #44 opened 4 years ago by SnoopyMark
  1

• Using CUDA 10.1

  #37 opened 4 years ago by tejas1995
  2

• how much computing resources do you spend to pretrain the model?

  #39 opened 4 years ago by junchen14
  2

• where can I find the category outputs for bottom-up features?

  #38 opened 4 years ago by homelifes
  2