RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn

[chenjingcheng]

python examples/refine_svg.py examples/test_assets/plane_oriented_init.svg examples/test_assets/plane_128.png
Using device: mps
iteration: 0
render loss: 0.23392434418201447
Traceback (most recent call last):
File "/Users/mac01/Documents/diffvg-torch/examples/refine_svg.py", line 133, in
main(args)
File "/Users/mac01/Documents/diffvg-torch/examples/refine_svg.py", line 102, in main
loss.backward()
File "/opt/miniconda3/envs/diffvg-torch/lib/python3.12/site-packages/torch/_tensor.py", line 630, in backward
torch.autograd.backward(
File "/opt/miniconda3/envs/diffvg-torch/lib/python3.12/site-packages/torch/autograd/init.py", line 364, in backward
_engine_run_backward(
File "/opt/miniconda3/envs/diffvg-torch/lib/python3.12/site-packages/torch/autograd/graph.py", line 865, in _engine_run_backward
return Variable._execution_engine.run_backward( # Calls into the C++ engine to run the backward pass
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn

If the device is cuda ,the result is same.