Hi,

I am a new PyTorch learner and got a problem recently in running the following code:

```
class CustomLoss(_Loss):
def forward(self, original, disparity, mag):
# original is the input
loss=0
target_overlap0=build_stack(original, 0, 1) # target_overlap0: num x 1 x w x h
target_overlap1=build_stack(original, 1, 1) # target_overlap1: num x 1 x w x h
target_overlap2=build_stack(original, 2, 1) # target_overlap2: num x 1 x w x h
target_overlap3=build_stack(original, 3, 1) # target_overlap3: num x 1 x w x h
target_mag1=build_stack(mag,1,1)
target_mag2=build_stack(mag,2,1)
target_mag3=build_stack(mag,3,1)
w=original.size()[3]
h=original.size()[2] # size()[3] and size()[2] are respectively the width and height of the image
disp=disparity[:,0,:,:] # take the first patch
# the second dimension is eliminated
theta=torch.FloatTensor([[1,0,0],[0,1,0]])
theta=theta.unsqueeze(0)
theta=theta.repeat(original.size()[0],1,1)
# original.size()[0] is the value of the patch size.
# '1' inside theta.repeat means it is exactly the same as the original argument.
# If '2' inside the function instead, it means to copy the original argument once.
theta=Variable(theta) # A kind of structure. For calculating gradients more conveniently.
grid_ori = F.affine_grid(theta, torch.Size((original.size()[0], 1, h, w)))
# Affine transformation
grid_ori=grid_ori.cuda(0)
grid_shift0=torch.stack((-1*disp/w/2, #5_5
-1*disp/h/2), dim=3)
grid1 = grid_ori + grid_shift0
warped_ori=F.grid_sample(target_overlap0, grid1, mode='bilinear')#, padding_mode='border')
warped_ori_w=warped_ori*target_mag1
target_overlap_w=target_overlap1*target_mag1
diff1=F.mse_loss(warped_ori_w, target_overlap_w)
grid_shift0=torch.stack((1*disp/w/2, #4_4
-1*disp/h/2),dim=3)
grid1=grid_ori+grid_shift0
warped_ori=F.grid_sample(target_overlap0, grid1, mode='bilinear')#, padding_mode='border')
warped_ori_w=warped_ori*target_mag2
target_overlap_w=target_overlap2*target_mag2
diff2=F.mse_loss(warped_ori_w, target_overlap_w)
# grid_shift0=torch.stack((-1*disp/w/2, #7_7
# 1*disp/h/2),dim=3)
grid_shift0=torch.stack((-1*disp/w/2, #7_7
1*disp/h/2),dim=3)
grid1=grid_ori+grid_shift0
warped_ori=F.grid_sample(target_overlap0, grid1, mode='bilinear')#, padding_mode='border')
warped_ori_w=warped_ori*target_mag3
target_overlap_w=target_overlap3*target_mag3
diff3=F.mse_loss(warped_ori_w, target_overlap_w)
# grid_shift0=torch.stack((1*disp/w/2, #8_8
# 1*disp/h/2),dim=3)
# grid1=grid_ori+grid_shift0
# warped_ori=F.grid_sample(target_overlap0, grid1, mode='bilinear')#, padding_mode='border')
# warped_ori_w=warped_ori*target_mag4
# target_overlap_w=target_overlap4*target_mag4
# diff4=F.mse_loss(warped_ori_w, target_overlap_w)
#
dx=gradx(disparity)[:,:,0:128,0:128]
dy=grady(disparity)[:,:,0:128,0:128]
TV=F.l1_loss(torch.abs(dx)+torch.abs(dy),0*disparity)
# loss= diff1+diff2+diff3+diff4#+0.000002*TV
loss= diff1+diff2+diff3+0.000002*TV
return loss
```

Error occurred in this statement:

```
grid1 = grid_ori + grid_shift0
```

But I checked the dimension of `grid_ori`

and `grid_shift0`

. They are actually the same. I donâ€™t know where this problem comes from. Is it a version problem?

Thank you all.