lucidrains/x-clip

Issues

• Text and Vision tokens different from CLIP

  #17 opened 10 months ago by MLRadfys
  0

• Loss in -ve

  #16 opened a year ago by yayati29
  0

• Bad Escape character Error

  #15 opened a year ago by wassimseif
  1

• some quesiton about x_clip

  #14 opened 2 years ago by chengyi-21
  0

• [DOCUMENTATION REQUEST] add demonstration for loading openai pretrained clip weights

  #6 opened 3 years ago by dmarx
  1

• extract features from CLIP with dim_text and dim_image other than 512

  #7 opened 2 years ago by abhishekaich27
  0

• Using different encoders in CLIP

  #12 opened 2 years ago by ethancohen123
  8

• Visual ssl with channels different than 3

  #11 opened 2 years ago by ethancohen123
  4

• Extract Text and Image Latents

  #13 opened 2 years ago by mmsamiei
  2

• NaN with mock data

  #10 opened 3 years ago by BlinkDL
  1

• Unable to train to convergence (small dataset)

  #9 opened 3 years ago by jacobwjs
  9

• Suggest your favorite papers to add!

  #1 opened 3 years ago by lucidrains
  20

• Model forward outputs to text/image similarity score

  #8 opened 3 years ago by paulcjh
  12

• Allow other types of visual SSL when initiating CLIP

  #5 opened 3 years ago by Froskekongen
  4