CGCL-codes/AMT-GAN

Issues

• CUDA device problem

  #21 opened 2 years ago by Leo1214
  1

• We do not know the matchup of the `(source, target)` for evaluation(i.e. we do not know the matchup of the images in different groups and the target identity that you have aimed) although you have uploaded `pair.zip` and `assets.zip`.

  #16 opened 2 years ago by yuuma002
  2

• 生成效果差

  #25 opened a year ago by ZTMIDGO
  0

• How to set the threshold on different datasets to evaluate the FR models using TAR@FAR？

  #24 opened a year ago by AaronSun2000
  0

• How to convert to ONNX

  #23 opened a year ago by ZTMIDGO
  0

• Why

  #22 opened a year ago by 1215372621
  0

• None

  #20 opened 2 years ago by csjunjun
  0

• LPIPS loss

  #19 opened 2 years ago by Werty18
  0

• attack success rate seems different from paper

  #18 opened 2 years ago by yuxu915
  1

• About multi-GPU training models

  #17 opened 2 years ago by godHhh
  1

• Could you provide the image `pairs` you have used for reproducing the result in Table.1 of the paper?

  #15 opened 2 years ago by yuuma002
  1

• Have the MI-FGSM, TI-DIM, and TIP-IM in the paper used the ensemble attack strategy, and are the maximum perturbation of PGD, MI-FGSM, TI-DIM, and TIP-IM all 16/255 under the L Infinity distance?

  #14 opened 2 years ago by GeorgeCarpenter
  3

• Some inconsistency between the paper and the repo

  #4 opened 2 years ago by GeorgeCarpenter
  3

• hello, could please provide code for test image quality?

  #13 opened 2 years ago by yuxu915
  1

• Hello, does the PGD attack in this paper use the integrated attack strategy

  #12 opened 2 years ago by SuperCarryFu
  7

• Pre-processing of face images/pretrained models/quantitative results

  #6 opened 2 years ago by Werty18
  3

• the question of training epoches

  #11 opened 2 years ago by Yueming6568
  1

• What's the `gamma` value of TIP-IM you have set for evaluating the performance of TIP-IM?

  #10 opened 2 years ago by GeorgeCarpenter
  1

• What's the calculation method of the SSIM value in the paper?

  #9 opened 3 years ago by zhoufengfan
  1

• How to change `IMG_SIZE`?

  #8 opened 3 years ago by samuelyutt
  2

• Can we feed the facenet model in the repo with the image whose size is (112, 112)?

  #7 opened 3 years ago by GeorgeCarpenter
  3

• Does the trained AMT-GAN generator can only attack a single target identity?

  #5 opened 3 years ago by GeorgeCarpenter
  1

• Cannot install skimage==0.0

  #3 opened 3 years ago by samuelyutt
  2

• Questions about the test set 1000 images from CelebA-HQ dataset

  #2 opened 3 years ago by samuel930930
  2

• Could you release your dataset and pre-trained models for reproducing your work?

  #1 opened 3 years ago by zhoufengfan
  2