MFM
MFM copied to clipboard
[ICLR 2023] Masked Frequency Modeling for Self-Supervised Visual Pre-Training
` # 2D FFT x_freq = torch.fft.fft2(image) # shift low frequency to the center x_freq = torch.fft.fftshift(x_freq, dim=(-2, -1)) # mask a portion of frequencies x_freq_masked = x_freq # restore...
loss for masking high frequency part, the loss mse of specturm goes to NaN. Why this happend?
I‘m so glad if you could help me with it.
Hi, authors. Thank you for the great work. I really enjoyed reading through your work. In the mean time, I got a question on the loss function (in the code)....
I'm excited by your work, I've done related experiments in the frequency domain before and didn't get better experimental results, you've given me new ideas, can you provide a copy...
thank you very much for your MFM !!! when i run (bash dist_finetune.sh ...) , get error how can i run (bash dist_finetune.sh ...) with only 1 gpu , not...