xiaoboCASIA/SV-X-Softmax

Issues

• one of the variables needed for gradient computation has been modified by an inplace operation: which is output 0 of MmBackward, is at version 1; expected version 0 instead. Hint: enable anomaly detection to find the operation that failed to compute its gradient, with torch.autograd.set_detect_anomaly(True).

  #9 opened 5 years ago by xysong1201
  2

• Training from scratch issues

  #5 opened 5 years ago by davidjimenezphd
  1

• do i need to modify softmax function?

  #3 opened 6 years ago by maryhh
  15

• Cloud you share your MS-Celeb-1M-v1c-R dataset.

  #8 opened 5 years ago by xysong1201
  0

• Will the Caffe version be released?

  #7 opened 5 years ago by ysc703
  0

• SV-X-Softmax源码

  #6 opened 5 years ago by xisi789
  5

• SV-cosface不收敛

  #1 opened 6 years ago by icodingc
  5

• There is no code files of this repo?

  #4 opened 6 years ago by yangxudong
  17

• the code is ready?

  #2 opened 6 years ago by twmht
  2