解决PyTorch报错：RuntimeError: Expected object of type torch.cuda.FloatTensor but found type torch.FloatT

小新GSUNG0222

于 2020-05-06 23:18:32 发布

阅读量1.2k

点赞数 3

CC 4.0 BY-SA版权

分类专栏： pytorch 文章标签： pytorch 深度学习

本文链接：https://blog.csdn.net/qq_36848732/article/details/105961997

1. 问题描述

1.1 在使用pytorch0.4.1推理pyramidbox 或者SSD时，发生以下报错：

RuntimeError: Expected object of type torch.cuda.FloatTensor but found type torch.FloatTensor for argument #2 'other'

在pytorch0.3上面应该时不报错的，改成0.4之后发生报错。

Traceback (most recent call last):
  File "test.py", line 241, in <module>
    det0 = detect_face(image, shrink)
  File "test.py", line 60, in detect_face
    y = net(x)
  File "....../lib/python3.6/site-packages/torch/nn/modules/module.py", line 477, in __call__
    result = self.forward(*input, **kwargs)
  File "....../pyramidbox/pyramid.py", line 452, in forward
    self.priors.type(type(x.data))   # default boxes
  File "....../pyramidbox/layers/functions/detection.py", line 46, in forward
    decoded_boxes = decode(loc_data[i], prior_data, self.variance)
  File "....../pyramidbox/layers/box_utils.py", line 231, in decode
    priors[:,

最低0.47元/天解锁文章