TypeError: can‘t convert CUDA tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory

TypeError: can’t convert CUDA tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first.

Traceback (most recent call last):
  File "train.py", line 436, in <module>
    train(hyp)  # train normally
  File "train.py", line 334, in train
    multi_label=ni > n_burn)
  File "/kyle/Pytorch-Spiking-YOLOv3-1/test.py", line 173, in test
    plot_images(imgs, output_to_target(output, width, height), paths=paths, names=names, fname=f)  # predictions
  File "/kyle/Pytorch-Spiking-YOLOv3-1/utils/utils.py", line 821, in output_to_target
    return np.array(targets)
  File "/home/a301/miniconda3/envs/spiking-YOLO-1/lib/python3.7/site-packages/torch/tensor.py", line 433, in __array__
    return self.numpy()
TypeError: can't convert CUDA tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first.

大意是:如果想把CUDA tensor格式的数据改成numpy时，需要先将其转换成cpu float-tensor随后再转到numpy格式。 numpy不能读取CUDA tensor 需要将它转化为 CPU tensor

将return self.numpy()改成return self.cpu().numpy()