icon-cookie
The website uses cookies to optimize your user experience. Using this website grants us the permission to collect certain information essential to the provision of our services to you, but you may change the cookie settings within your browser any time you wish. Learn more
I agree
Summary | 15 Annotations
ATen’s API is auto-generated from the same declarations PyTorch uses so the two APIs will track each other over time.
2020/08/31 06:57
Accessors then expose an API for accessing the Tensor elements efficiently.
2020/08/31 07:00
Accessors are temporary views of a Tensor. They are only valid for the lifetime of the tensor that they view and hence should only be used locally in a function, like iterators.
2020/08/31 07:00
accessors are not compatible with CUDA tensors
2020/08/31 07:00
recommended to use accessors for CPU tensors and packed accessors for CUDA tensors
2020/08/31 07:01
.accessor<float,2>()
2020/08/31 07:02
.packed_accessor64<float,2>()
2020/08/31 07:02
quite a bit faster on CUDA
2020/08/31 07:03
may lead to overflows
2020/08/31 07:03
32
2020/08/31 07:03
32
2020/08/31 07:03
from_blob
2020/08/31 07:04
cannot be resized
2020/08/31 07:04
Scalars can be implicitly constructed from C++ number types
2020/08/31 07:05
allows Tensor objects to be zero-dimensional
2020/08/31 07:06