import pysdtw

device = torch.device("cuda")

# the input data includes a batch dimension
X = torch.rand((10, 5, 7), requires_grad=True).to(device)
Y = torch.rand((10, 9, 7)).to(device)

# optionally choose a pairwise distance function
fun = pysdtw.distance.pairwise_l2_squared

# create the SoftDTW distance function
sdtw = pysdtw.SoftDTW(gamma=1.0, dist_func=fun, use_cuda=True)

# soft-DTW discrepancy, approaches DTW as gamma -> 0
res = sdtw(X, Y)

# define a loss, which gradient can be backpropagated
loss = res.sum()
loss.backward()

# X.grad now contains the gradient with respect to the loss

/usr/local/lib/python3.7/dist-packages/torch/_tensor.py:1083: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want the .grad field to be populated for a non-leaf Tensor, use .retain_grad() on the non-leaf Tensor. If you access the non-leaf Tensor by mistake, make sure you access the leaf Tensor instead. See github.com/pytorch/pytorch/pull/30531 for more informations. (Triggered internally at  aten/src/ATen/core/TensorBody.h:477.)
  return self._grad