henghuiding/Vision-Language-Transformer

Issues

• Test with own dataset

  #18 opened 2 months ago by wooj0216
  2

• swin transformer 做视觉特征提取器

  #17 opened 10 months ago by liujing0814
  0

• Reproducing on refcocog

  #16 opened 10 months ago by freshpearYoon
  0

• how to resume training from previous epoch?

  #15 opened 10 months ago by freshpearYoon
  0

• question about loader.py

  #14 opened a year ago by freshpearYoon
  0

• some questions of environment error and refG's overIoU in the paper

  #12 opened a year ago by xiejialong
  2

• Run this repository on the latest version or the same as the author's?

  #13 opened a year ago by Shuaicong97
  0

• Problem: AttributeError: 'tuple' object has no attribute 'layer'

  #9 opened 2 years ago by FioPio
  9

• code about contrastive learning

  #11 opened 2 years ago by Chic-J
  0

• Corresponding code for the Query Generation Module

  #10 opened 2 years ago by KevinGoodman
  0

• Confusion about data_process_v2

  #8 opened 2 years ago by huangjy-pku
  0

• What's the gpu device that can support this model?

  #2 opened 3 years ago by sennnnn
  4

• How to inference on my own image and text？

  #7 opened 2 years ago by kelisiya
  1

• About training speed.

  #4 opened 3 years ago by chaoqunwangcs
  2

• How to perform Inference?

  #5 opened 3 years ago by YunLongPan
  3

• How to train on the custom data set?

  #3 opened 3 years ago by YunLongPan
  2

• Two questions about the model training: weight mismatch and yolov3_480000.h5

  #1 opened 3 years ago by jianhua2022
  1