torch.from_numpy
-
torch.from_numpy(ndarray) → Tensor
-
Creates a
Tensor
from anumpy.ndarray
.The returned tensor and
ndarray
share the same memory. Modifications to the tensor will be reflected in thendarray
and vice versa. The returned tensor is not resizable.It currently accepts
ndarray
with dtypes ofnumpy.float64
,numpy.float32
,numpy.float16
,numpy.complex64
,numpy.complex128
,numpy.int64
,numpy.int32
,numpy.int16
,numpy.int8
,numpy.uint8
, andnumpy.bool
.Example:
>>> a = numpy.array([1, 2, 3]) >>> t = torch.from_numpy(a) >>> t tensor([ 1, 2, 3]) >>> t[0] = -1 >>> a array([-1, 2, 3])
© 2019 Torch Contributors
Licensed under the 3-clause BSD License.
https://pytorch.org/docs/1.8.0/generated/torch.from_numpy.html