yunqing-me/AttackVLM

Issues

• Where are the implementations of MF-it?

  #16 opened a month ago by yechao-zhang
  1

• GradCAM Visualization

  #21 opened a month ago by jdg900
  1

• Minigpt4 code problerm

  #22 opened 2 months ago by returnaaa
  5

• What models are used for img2prompt and LLAVA

  #18 opened 10 months ago by kz29
  3

• Blip2OPT' object has no attribute 'forward_encoder_image'

  #17 opened 10 months ago by kz29
  1

• Segmentation fault when doing `clip_model.encode_image`

  #20 opened 7 months ago by lingzhiyxp
  1

• It seems that it can only be run on a single card. Is there a multi-card version?

  #19 opened 7 months ago by sftsgly
  0

• Is your method black-box or gray-box？

  #13 opened 9 months ago by 1057939502
  1

• Questions about attack on BLIP (LAVIS)

  #7 opened a year ago by ericyinyzy
  3

• Reproducing MF-it result in Table 2 of the paper

  #10 opened a year ago by HashmatShadab
  4

• 可以用3090嘛

  #15 opened a year ago by alex1243423
  1

• Why only using the first dimension of the image encoding?

  #14 opened a year ago by Yuancheng-Xu
  0

• dimension mismatch in code

  #12 opened a year ago by 18445864529
  3

• Question regarding the generation of adversarial examples

  #9 opened a year ago by Sammy42779
  1

• Regarding data path in LAVIS

  #11 opened a year ago by 18445864529
  1

• The large model you just updated includes Unidiff, MiniGPT-4 and LAVIS, but it is not mentioned in the LAVIS paper. I would like to ask what model this is, and how to reproduce several large models in the paper?For example, BLIP, BLIP2, etc.

  #5 opened a year ago by LKJ-np
  1

• MiniGPT-4 Code

  #6 opened a year ago by LKJ-np
  1

• Connot interpret 'torch.float32' as a data type

  #8 opened a year ago by LKJ-np
  1

• VLM model

  #4 opened a year ago by LKJ-np
  2

• data question

  #2 opened a year ago by LKJ-np
  5

• Import package problem

  #3 opened a year ago by LKJ-np
  0

• We couldn't connect to 'https://huggingface.co' to load this model, couldn't find it in the cached files and it looks like CompVis/stable-diffusion-safety-checker is not the path to a directory containing a config.json file. Checkout your internet connection or see how to run the library in offline mode at 'https://huggingface.co/docs/transformers/installation#offline-mode'

  #1 opened a year ago by LKJ-np
  6