python - 如何从 PyTorch 网络中的稀疏矩阵获取后向梯度？

Question

我正在关注 PyTorch 教程示例:

https://pytorch.org/tutorials/beginner/pytorch_with_examples.html

该示例运行没有任何问题，但是当我将其切换到我自己的数据集(这是一个稀疏张量，因为它太大而无法用作稠密张量)时，我遇到了以下错误:

RuntimeError                              Traceback (most recent call last)
<ipython-input-127-8b4999644085> in <module>()
 41     # Backward pass: compute gradient of the loss with respect to model
 42     # parameters
---> 43     loss.backward()
 44 
 45     # Calling the step function on an Optimizer makes an update to its

~/miniconda3/envs/py3/lib/python3.6/site-packages/torch/tensor.py in backward(self, gradient, retain_graph, create_graph)
 91                 products. Defaults to ``False``.
 92         """
---> 93         torch.autograd.backward(self, gradient, retain_graph, create_graph)
 94 
 95     def register_hook(self, hook):

~/miniconda3/envs/py3/lib/python3.6/site-packages/torch/autograd/__init__.py in backward(tensors, grad_tensors, retain_graph, create_graph, grad_variables)
 87     Variable._execution_engine.run_backward(
 88         tensors, grad_tensors, retain_graph, create_graph,
---> 89         allow_unreachable=True)  # allow_unreachable flag
 90 
 91 

RuntimeError: Expected object of type torch.FloatTensor but found type torch.sparse.FloatTensor for argument #2 'mat2'

我尝试切换优化器(Adagrad、Adam)，但似乎不起作用。

编辑:添加了更多错误输出。错误发生在 backward()

Answer 1

看起来这个功能目前正在开发中。

https://github.com/pytorch/pytorch/issues/2389