LDDMM error: IndexError: index 1 is out of bounds for dimension 0 with size 1

[OMIC-coding]

---

IndexError Traceback (most recent call last)
Cell In[132], line 26
10 # keep all other parameters default
11 params = {'L':L,'T':T,
12 'niter': 200,
13 'pointsI': pointsI,
(...)
23 'epV': 5e1
24 }
---> 26 out = STalign.LDDMM([YI,XI], I, [YJ,XJ], J, **params)

File ~/.local/lib/python3.10/site-packages/STalign/STalign.py:1074, in LDDMM(xI, I, xJ, J, pointsI, pointsJ, L, T, A, v, xv, a, p, expand, nt, niter, diffeo_start, epL, epT, epV, sigmaM, sigmaB, sigmaA, sigmaR, sigmaP, device, dtype, muB, muA)
1072 else:
1073 raise Exception(f'If inputting an initial v, must input both xv and v')
-> 1074 extentV = extent_from_x(xv)
1075 dv = torch.as_tensor([x[1]-x[0] for x in xv],device=device,dtype=dtype)
1079 fv = [torch.arange(n,device=device,dtype=dtype)/n/d for n,d in zip(XV.shape,dv)]

File ~/.local/lib/python3.10/site-packages/STalign/STalign.py:857, in extent_from_x(xJ)
834 def extent_from_x(xJ):
835 ''' Given a set of pixel locations, returns an extent 4-tuple for use with np.imshow.
836
837 Note inputs are locations of pixels along each axis, i.e. row column not xy.
(...)
855
856 '''
--> 857 dJ = [x[1]-x[0] for x in xJ]
858 extentJ = ( (xJ[1][0] - dJ[1]/2.0).item(),
859 (xJ[1][-1] + dJ[1]/2.0).item(),
860 (xJ[0][-1] + dJ[0]/2.0).item(),
861 (xJ[0][0] - dJ[0]/2.0).item())
862 return extentJ

File ~/.local/lib/python3.10/site-packages/STalign/STalign.py:857, in (.0)
834 def extent_from_x(xJ):
835 ''' Given a set of pixel locations, returns an extent 4-tuple for use with np.imshow.
836
837 Note inputs are locations of pixels along each axis, i.e. row column not xy.
(...)
855
856 '''
--> 857 dJ = [x[1]-x[0] for x in xJ]
858 extentJ = ( (xJ[1][0] - dJ[1]/2.0).item(),
859 (xJ[1][-1] + dJ[1]/2.0).item(),
860 (xJ[0][-1] + dJ[0]/2.0).item(),
861 (xJ[0][0] - dJ[0]/2.0).item())
862 return extentJ

IndexError: index 1 is out of bounds for dimension 0 with size 1

[OMIC-coding]

A simple affine alignment is needed to align the single-cell spatial transcriptomics dataset with the H&E staining image. So I performed non-linear local alignments via LDDMM. However, I encountered the bug illustrated as above.