OSV-q The size of tensor a (3) must match the size of tensor b (320) at non-singleton dimension 3

    lap = -(cmul(fft2(grd_x), cconj(fft2(grd_x), inplace=False)) + cmul(fft2(grd_y), cconj(fft2(grd_y), inplace=False)))
  File "C:/Users/shang/Desktop/STDN_LI/TVGnet/OSV_q.py", line 132, in cconj
    c = t.clone() if not inplace else t
AttributeError: 'numpy.ndarray' object has no attribute 'clone'

  hold ‘clone’ Change to ‘copy’ Unified type , Then I wrote new code

 lap = -(conjoDx * otfDx + conjoDy * otfDy)
 pdf1 = miu2 * (lap * fft2(f - output_net - b2)) - karma * (conjoDx * fft2(q1) + conjoDy * fft2(q2))

There is a problem , The dimensions are not consistent ,

hold fft2 Each parameter dimension in has been changed to be consistent , Or an error

  File "C:/Users/shang/Desktop/STDN_LI/TVGnet/OSV_q.py", line 391, in <module>
    train(opt)
  File "C:/Users/shang/Desktop/STDN_LI/TVGnet/OSV_q.py", line 320, in train
    pdf1 = miu2 * (lap * fft2(f - output_net - b2)) - karma * (conjoDx * fft2(q1) + conjoDy * fft2(q2))
RuntimeError: The size of tensor a (3) must match the size of tensor b (320) at non-singleton dimension 3

Process finished with exit code 1

3.22 Because the code has been depressed for a long time , The school is still closed , In a very bad mood

I had a good look again today , Decide not to fool around anymore , Still have to find a way , You can't feel it , I finally found ,

http://t.csdn.cn/mqK82

Sure enough, calm down and you'll be fine . Carefully analyzed this error . It is found that several numerical dimensions in the error report do not match

b1 = {Tensor:(1,3,320,320)} 
b2 = {Tensor:(1,3,320,320)} 

f = {Tensor:(1,320,320,3)} 

output_net = {Tensor:(1,3,320,320)} 

After so long, it turned out to be f Dimension problem of , I'm so angry , Do it ！

because b1 b2 In the code is and f equal , So I just modified f The dimension of is good .

 f = img_in.clone()
 f = f.permute(2, 0, 1)
 f = f.unsqueeze(0)

There is no dimension error , But there are still errors in this line

====>> Sat Mar 12 11:01:15 2022   Pass time: 0:00:17.422007
Traceback (most recent call last):
  File "C:/Users/shang/Desktop/STDN_LI/TVGnet/OSV_q.py", line 392, in <module>
    train(opt)
  File "C:/Users/shang/Desktop/STDN_LI/TVGnet/OSV_q.py", line 321, in train
    pdf1 = miu2 * (lap * fftn(f - output_net - b2)) - karma * (conjoDx * fftn(q1) + conjoDy * fftn(q2))
RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!

Process finished with exit code 1

changes

    f = img_in.clone()
    f = f.permute(2, 0, 1)
    f = f.unsqueeze(0).type(torch.LongTensor).to(device)

Not sure, right , But the problem has changed  

====>> Sat Mar 12 11:45:10 2022   Pass time: 0:00:16.835837
Traceback (most recent call last):
  File "C:/Users/shang/Desktop/STDN_LI/TVGnet/OSV_q.py", line 390, in <module>
    train(opt)
  File "C:/Users/shang/Desktop/STDN_LI/TVGnet/OSV_q.py", line 319, in train
    pdf1 = miu2 * (lap * fftn(f - output_net - b2)) - karma * (conjoDx * fftn(q1) + conjoDy * fftn(q2))
ValueError: operands could not be broadcast together with shapes (348,348) (1,3,320,320) 

Process finished with exit code 1

  Error reporting here , I defined lap The value is （348,348）, Should be tensor Broadcast error , Continue to study this problem

I found it

  h, w, c = img_in.shape
  nw, nh = w - w % d, h - h % d

  #  It turned out to be like this 
 otfDx = psf2otf(Dh_psf, [h, w])
 otfDy = psf2otf(Dv_psf, [h, w])

  #  Change it to 
 otfDx = psf2otf(Dh_psf, [nh, nw])
 otfDy = psf2otf(Dv_psf, [nh, nw])

This line is finally correct

====>> Sat Mar 12 15:13:59 2022   Pass time: 0:00:17.143842
Traceback (most recent call last):
  File "C:/Users/shang/Desktop/STDN_LI/TVGnet/OSV_q.py", line 390, in <module>
    train(opt)
  File "C:/Users/shang/Desktop/STDN_LI/TVGnet/OSV_q.py", line 322, in train
    z = z.real.detach().clone()
AttributeError: 'numpy.ndarray' object has no attribute 'detach'

Process finished with exit code 1