Jiahao000/MFM

Issues

• How to save the frequency domain image after FFT operation？

  #2 opened a year ago by AbandonedWarlord
  1

• NaN for low pass branch in training

  #7 opened 9 months ago by KlZOnmyway
  1

• The article states that the decoder uses a linear layer, but the pre-training code uses Conv2d, and I'm confused about this.

  #6 opened 9 months ago by shidanW
  0

• Question about loss in the code

  #5 opened 9 months ago by shidanW
  0

• Question about computing loss in the code

  #4 opened a year ago by cooma04
  0

• can you provide a copy of the pretrain model for visualizing the test images in test.py？

  #3 opened a year ago by AbandonedWarlord
  0

• i only have 1 gpu , how can i run (bash dist_finetune.sh ...)

  #1 opened 2 years ago by 565ee
  1