luo3300612/image-captioning-DLCT

Issues

• ModuleNotFoundError: No module named 'grid_feats'

  #48 opened 6 months ago by zdpaa
  0

• 预训练模型结果较低

  #47 opened 8 months ago by ImaginationCreater
  0

• TypeError: __init__() got an unexpected keyword argument 'd_model'

  #46 opened 9 months ago by MapleFigure
  0

• TypeError: 'generator' object is not callable

  #40 opened 2 years ago by 5132210
  3

• error

  #45 opened 10 months ago by zdpaa
  0

• 测试过程中遇到的词表长度问题

  #37 opened 3 years ago by tianjunyu0871
  1

• 怎么评估spice分数

  #31 opened a year ago by haijie945
  2

• ImportError: cannot import name 'PTBTokenizer' from 'evaluation'

  #27 opened 3 years ago by shy123456-willow
  3

• Reinforcement learning generates an incomplete description？

  #44 opened 2 years ago by Xiong-can
  1

• 关于evaluation阶段的报错

  #22 opened 3 years ago by yanjialele
  7

• coco_test数据集特征

  #33 opened 3 years ago by lc080113
  4

• 提取区域特征？

  #39 opened 2 years ago by xiaohe0405
  2

• 想获取ResNeXt-152数据集

  #41 opened 2 years ago by bacon-yu
  1

• Questions about h5py.File features on customized images!

  #2 opened 4 years ago by liman13552763129
  10

• GET缺少global_transformer_glu模块

  #43 opened 2 years ago by ccccchenllll
  0

• LCCA模块的图结构是用多头注意力实现的？

  #42 opened 2 years ago by kangkang189
  0

• Can you upload resources to another cloud like Gdrive, Onedrive or Dropbox?

  #17 opened 3 years ago by khiemledev
  5

• 关于GET模型的train.py文件

  #38 opened 2 years ago by hzf-hhh
  0

• 关于pth大小

  #26 opened 2 years ago by haijie945
  1

• 区域特征提取

  #24 opened 2 years ago by HN123-123
  2

• About visualization code

  #25 opened 3 years ago by aichisuancai
  2

• The Code to generate the caption of a figure.

  #34 opened 3 years ago by z972778371
  1

• RL training stage, out of memory

  #13 opened 3 years ago by TBI805
  4

• 关于训练阶段Shuffle参数设置问题

  #23 opened 3 years ago by yanjialele
  2

• TypeError: __init__() got an unexpected keyword argument 'train_on_pred_boxes'

  #30 opened 3 years ago by hwbhwbgao
  4

• Unable to download the pretrained model

  #36 opened 3 years ago by luileito
  0

• RuntimeError: stack expects each tensor to be equal size

  #35 opened 3 years ago by competent-s
  4

• 数据集特征提取

  #32 opened 3 years ago by yanjialele
  0

• Expected all tensors to be on the same device

  #29 opened 3 years ago by maryawwm
  0

• Unable to load pretrained_model.pth

  #28 opened 3 years ago by yvfengZhong
  0

• What is the relation between X-101 and X-152 extractors in the code?

  #9 opened 3 years ago by hcl14
  1

• how are alignment graph obtained for new datasets

  #19 opened 3 years ago by Davidwdq
  1

• can_be_stateful 参数的含义

  #20 opened 3 years ago by amazingYX
  2

• A code bug

  #14 opened 3 years ago by GX77
  2

• 训练好的model

  #15 opened 3 years ago by a75732410
  2

• Can you share the pretrained model?

  #10 opened 3 years ago by hcl14
  1

• Concept Question about MHLCCA

  #8 opened 3 years ago by TCBpenta8
  1

• 交叉熵性能

  #12 opened 3 years ago by hasky123
  1

• IndexError: invalid index to scalar variable

  #16 opened 3 years ago by zghorbani
  1

• where is the path_of_model_to_eval.pth ?

  #7 opened 3 years ago by whqwill
  2

• About features on Baiduyun disk

  #4 opened 3 years ago by john2019-warwick
  3

• Should ['%d_size' % image_id] be equal to the real image size?

  #11 opened 3 years ago by hcl14
  1

• parameter error

  #6 opened 4 years ago by lixiangpengcs
  1

• About test performance

  #5 opened 4 years ago by wanboyang
  4

• coco_all_align.zip file error

  #3 opened 4 years ago by fuchao01
  0

• Feature extraction on customized images

  #1 opened 4 years ago by ltp1995
  1