项目场景：

运行程序，出现报错信息 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 "tools/demo.py", line 97, in <module>visualize_result(gallery_img, detections, similarities)File "tools/demo.py", line 41, in visualize_result(x1, y1), x2 - x1, y2 - y1, fill=False, edgecolor="#4CAF50", linewidth=3.5File "/environment/miniconda3/lib/python3.7/site-packages/matplotlib/axes/_base.py", line 2358, in add_patchself._update_patch_limits(p)File "/environment/miniconda3/lib/python3.7/site-packages/matplotlib/axes/_base.py", line 2381, in _update_patch_limitspatch_trf = patch.get_transform()File "/environment/miniconda3/lib/python3.7/site-packages/matplotlib/patches.py", line 278, in get_transformreturn self.get_patch_transform() + artist.Artist.get_transform(self)File "/environment/miniconda3/lib/python3.7/site-packages/matplotlib/patches.py", line 752, in get_patch_transformbbox = self.get_bbox()File "/environment/miniconda3/lib/python3.7/site-packages/matplotlib/patches.py", line 845, in get_bboxreturn transforms.Bbox.from_extents(x0, y0, x1, y1)File "/environment/miniconda3/lib/python3.7/site-packages/matplotlib/transforms.py", line 839, in from_extentsbbox = Bbox(np.reshape(args, (2, 2)))File "<__array_function__ internals>", line 6, in reshapeFile "/home/featurize/work/.local/lib/python3.7/site-packages/numpy/core/fromnumeric.py", line 298, in reshapereturn _wrapfunc(a, 'reshape', newshape, order=order)File "/home/featurize/work/.local/lib/python3.7/site-packages/numpy/core/fromnumeric.py", line 54, in _wrapfuncreturn _wrapit(obj, method, *args, **kwds)File "/home/featurize/work/.local/lib/python3.7/site-packages/numpy/core/fromnumeric.py", line 43, in _wrapitresult = getattr(asarray(obj), method)(*args, **kwds)File "/home/featurize/work/.local/lib/python3.7/site-packages/torch/tensor.py", line 458, in __array__return self.numpy()
TypeError: can't convert CUDA tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first.

---

问题描述

这个问题是由 python 3.7 版本引起的。修改部分 python 源码即可。

根据报错信息，定位到 /home/featurize/work/.local/lib/python3.7/site-packages/torch/tensor.py

---

解决方案：

将 self.numpy() 改成 self.cpu().numpy()，即找到 tensor.py 的第 458 行

    def __array__(self, dtype=None):if dtype is None:return self.numpy()else:return self.numpy().astype(dtype, copy=False)

改成