Linwei-Chen/FreqFusion

Issues

• 关于Initial fusion

  #38 opened 16 days ago by P20000911
  1

• 关于SegNeXt中实例化freqfusion中通道平均压缩的操作

  #37 opened 22 days ago by Ronin-711
  0

• 与原文流程图理解问题

  #36 opened 23 days ago by Fuzm7
  2

• About carafe

  #14 opened 3 months ago by DuowenC
  12

• 关于segformer使用推荐

  #35 opened a month ago by SuGuilin
  1

• 关于offset生成器的一些问题

  #34 opened a month ago by LIyyyy98
  2

• Freqfusion如何在Segformer解码器使用？

  #16 opened 3 months ago by StephenZhou98
  5

• 论文中流程图的理解问题

  #33 opened a month ago by hbaiabai
  2

• RuntimeError: carafe_forward_impl: implementation for device cpu not found.

  #6 opened a month ago by mqdigihub
  5

• 您好。想请问以下使用FreqFusion的位置和方式有什么注意的吗？我使用了之后效果是变差的。

  #32 opened a month ago by lcl-git-3d
  5

• assert m_c == kernel_size ** 2 * up ** 2 关于这个报错

  #21 opened 2 months ago by Mrrfu
  4

• 您好，想请问一下，代码中lowpass_kernel和highpass_kernel的值是怎么设置的，有什么根据吗

  #31 opened 2 months ago by Run-19
  1

• 偏移生成器中分组策略的意义是什么，该如何理解？

  #30 opened 2 months ago by Satama1
  0

• 偏移生成器中分组策略的意义是什么，该如何理解？

  #29 opened 2 months ago by Satama1
  0

• 关于图6中的(e)和(f)

  #27 opened 2 months ago by zsl9772
  2

• 为什么低通滤波生成器反而依赖于高频分量？

  #28 opened 2 months ago by Satama1
  1

• ALPF generator中4×K^2×1×1的中间结果是如何得到的

  #26 opened 2 months ago by llgnll
  7

• Why does ALPF generator rely on high-frequency components of features?

  #23 opened 2 months ago by WesternTrail
  3

• RuntimeError: Input type (torch.cuda.FloatTensor) and weight type (torch.FloatTensor) should be the same

  #7 opened 3 months ago by jiajia65
  11

• 请问高通滤波时如何通过减法计算出来的

  #25 opened 2 months ago by lshqi
  1

• About Fig 9 in the paper.

  #24 opened 2 months ago by Q-M-E
  1

• FAQ 解答

  #3 opened 3 months ago by Linwei-Chen
  24

• 关于尺寸不匹配报错

  #22 opened 2 months ago by DuowenC
  2

• Update

  #20 opened 2 months ago by Linwei-Chen
  1

• IndexError: _Map_base::at

  #19 opened 2 months ago by luoqianhao
  2

• Can FreqFusion be applied in nnunetv2 to segment 3D medical image data？？

  #18 opened 2 months ago by liangzw599
  1

• 改动到FPN结构上报错ext_module.carafe_backward( RuntimeError: CUDA error: invalid configuration argument

  #17 opened 2 months ago by omnipotenttom
  3

• Enhancing Initial Fusion部分代码看不懂

  #15 opened 3 months ago by yx-yyds
  4

• 您好，请问如何绘制图1中的类内相似性图？

  #13 opened 3 months ago by gsxzz
  3

• 关于ALPF generator，AHPF generator以及Offset generator的理解

  #12 opened 3 months ago by windyjunfeng
  2

• 不是很理解ALPF和AHPF如何做到低通和高通的？

  #11 opened 3 months ago by lmomoy
  1

• 使用问题

  #10 opened 3 months ago by Muzi010
  10

• RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [1, 1, 3, 3]] is at version 3; expected version 2 instead. Hint: the backtrace further above shows the operation that failed to compute its gradient. The variable in question was changed in there or anywhere later. Good luck!

  #9 opened 3 months ago by SIGMACX
  2

• AssertionError

  #8 opened 3 months ago by jiajia65
  1

• FreqFusionCARAFEFPN缺失

  #2 opened 3 months ago by CLuKing
  15

• Size prob

  #5 opened 3 months ago by CaipingPeng
  5

• 运行问题

  #4 opened 3 months ago by Muzi010
  5

• Comming Soon!

  #1 opened 4 months ago by carfei
  1