YoadTew/zero-shot-image-to-text

Issues

• How the entire dataset is converted into captions

  #15 opened a year ago by shams2023
  4

• run.py

  #18 opened a year ago by deyi89
  0

• Questions about modifying context cache?

  #13 opened a year ago by Kingofolk
  5

• the generated caption effect is not good（The main reason is that the resolution of the picture is too low）

  #17 opened a year ago by shams2023
  0

• Precict.py Question

  #16 opened a year ago by shams2023
  0

• I encountered a problem while running the code. Please help me solve it. Thank you

  #14 opened a year ago by shams2023
  0

• UnboundLocalError - 'context' reference before assignment

  #6 opened 2 years ago by daurmur
  7

• in model/ZeroCLIP.py tmp_weights in 290 row is not used

  #8 opened 2 years ago by hl123-123
  1

• Should I additionally set end_factor to 1.04 in the command and set the variable self.ef_idx to 3 in class CLIPTextGenerator to reproduce image caption results?

  #12 opened 2 years ago by baiyuting
  1

• Any evaluate script provided to quickly calculate the metrics in this paper?

  #11 opened 2 years ago by baiyuting
  1

• Question about the cache update

  #10 opened 2 years ago by Richar-Du
  0

• About Eq.(5) in paper

  #9 opened 2 years ago by 232525
  0

• time-step in code

  #5 opened 2 years ago by heliossun
  1

• Metrics Computations : B@1 = BLEU-1, M = METEOR, C = CIDEr, S = SPICE.

  #7 opened 2 years ago by aliman80
  0

• Colab notebook availability

  #4 opened 3 years ago by virtualramblas
  0