You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I solved the problem where the usage of the warp_grid property of the HomographyWarper class was changed in this way:
Replace 'flowCoarse = warper.warp_grid(bestPara)' with
warper = tgm.HomographyWarper(I1Tensor.size()[2], I1Tensor.size()[3])
grid = warper.warp_grid(torch.from_numpy(bestParam.astype(np.float32)).unsqueeze(0).cuda())
作者您好,我在运行这段代码时会报错AttributeError: 'HomographyWarper' object has no attribute 'warp_grid',您知道是为什么吗
The text was updated successfully, but these errors were encountered: