[人工智能]解决：lstm repackage_hidden() TypeError: iteration over a 0-d tensor

项目场景：

LSTM训练

问题描述：

Traceback (most recent call last):
  File "sample.py", line 81, in <module>
    sample_stroke()
  File "sample.py", line 42, in sample_stroke
    [strokes, params] = model.sample(sample_args.sample_length)
  File "/root/Handwriting/RNN-Handwriting-Generation-Pytorch-master/model.py", line 110, in sample
    eos, pi, mu1, mu2, sigma1, sigma2, rho = self.forward(prev_x)
  File "/root/Handwriting/RNN-Handwriting-Generation-Pytorch-master/model.py", line 65, in forward
    self.hidden = self.repackage_hidden(self.hidden)
  File "/root/Handwriting/RNN-Handwriting-Generation-Pytorch-master/model.py", line 46, in repackage_hidden
    return tuple(self.repackage_hidden(v) for v in h)
  File "/root/Handwriting/RNN-Handwriting-Generation-Pytorch-master/model.py", line 46

了解本专栏 订阅专栏 解锁全文 学习会员免费看 赠12个月