小编Om *_*ogi的帖子

当我运行 pytorch matmul 时，抛出以下错误：

Traceback (most recent call last):
  File "/home/omrastogi/Desktop/Side/One-Class-Classification-Customer-Complaints/pattern.py", line 71, in <module>
    print(obj.infer(list([df.text[0]]), list([df.reason[0]])))
  File "/home/omrastogi/Desktop/Side/One-Class-Classification-Customer-Complaints/pattern.py", line 45, in infer
    cos_sm = self.batch_cosine_similarity(enc1, enc2)
  File "/home/omrastogi/Desktop/Side/One-Class-Classification-Customer-Complaints/pattern.py", line 51, in batch_cosine_similarity
    dot_prd = torch.matmul(inp1, inp2.transpose(0, 1))
RuntimeError: "addmm_impl_cpu_" not implemented for 'Half'

inp1 --> [1 256]
inp2 --> [1 256]

fig,ax = plt.subplots()
ax.set_xlim(0,500)
ax.set_ylim(0,500)
scatter, = ax.scatter(x_arr,y_arr)
plt.show()

在 scatter 语句中，程序出现了此错误。我不明白可能是什么问题。

---
TypeError                                 Traceback (most recent call last)
<ipython-input-26-b70b84828456> in <module>
      6 ax.set_xlim(0,500)
      7 ax.set_ylim(0,500)
----> 8 scatter, = ax.scatter(x_arr,y_arr)
      9 plt.show()

TypeError: cannot unpack non-iterable PathCollection object