Philip-Bachman/amdim-public

Issues

• Two pre-trained models are not downloading

  #17 opened 2 years ago by nanacoco419
  1

• Are amount of negative samples large?

  #18 opened 2 years ago by xinyaojiejie
  0

• Expectation of N7 in equation (1)

  #12 opened 3 years ago by martinmamql
  2

• time for training self-supervised and pretrained models

  #14 opened 5 years ago by georgecloudservices
  1

• Truly multi-view datasets

  #13 opened 5 years ago by bkj
  1

• Questions about Mixture-Based Representations

  #9 opened 3 years ago by Wuziyi616
  0

• training self sueprvised learning on multi-gpu

  #16 opened 4 years ago by bhat-prashant
  0

• Which python command are you using for CIFAR and STL10 experiments?

  #3 opened 5 years ago by LIUNancy
  6

• Why don't u use Resnet50 or any normal architectures?

  #10 opened 5 years ago by abcdvzz
  1

• urgent - how is positive and negative samples defined

  #11 opened 5 years ago
  7

• while in the test time, what dose the _warmup_batchnorm do?

  #8 opened 5 years ago by victor000000
  1

• what does lgt_reg mean, is it the entropy maximization term H(q)?

  #7 opened 5 years ago by victor000000
  2

• The effect of multi-scale features

  #6 opened 5 years ago by wangxu-scu
  0

• Details of Auto-augment to get the best results

  #5 opened 5 years ago by XingyuJinTI
  4

• Question about training self-supervised model

  #4 opened 5 years ago by 0three
  5

• How to avoid the grad from labels influencing the info_modules?

  #2 opened 5 years ago by munanning
  2