pytorch使用记录（五） 关于tensor、PIL以及numpy转换的问题

最近在运行程序的时候一直出现如下错误：

  File "/home/daydayjump/Glow/glow/trainer.py", line 172, in train
    self.writer.add_image("1_prob/{}".format(bi), plot_prob([y_pred[bi], y_true[bi]], ["pred", "true"]).cuda().float(), self.global_step)
  File "/home/daydayjump/anaconda3/lib/python3.7/site-packages/tensorboardX/writer.py", line 427, in add_image
    image(tag, img_tensor, dataformats=dataformats), global_step, walltime)
  File "/home/daydayjump/anaconda3/lib/python3.7/site-packages/tensorboardX/summary.py", line 216, in image
    image = make_image(tensor, rescale=rescale)
  File "/home/daydayjump/anaconda3/lib/python3.7/site-packages/tensorboardX/summary.py", line 254, in make_image
    image = Image.fromarray(tensor)
  File "/home/daydayjump/anaconda3/lib/python3.7/site-packages/PIL/Image.py", line 2517, in fromarray
    raise TypeError("Cannot handle this data type")
Typ