/home/docs/checkouts/readthedocs.org/user_builds/advanced-micro-devices-roccv/checkouts/latest/include/core/tensor_requirements.hpp Source File

/home/docs/checkouts/readthedocs.org/user_builds/advanced-micro-devices-roccv/checkouts/latest/include/core/tensor_requirements.hpp Source File#

2 min read time

Applies to Linux

rocCV: /home/docs/checkouts/readthedocs.org/user_builds/advanced-micro-devices-roccv/checkouts/latest/include/core/tensor_requirements.hpp Source File
tensor_requirements.hpp
Go to the documentation of this file.
1 
23 #pragma once
24 
25 #include "data_type.hpp"
26 #include "tensor_layout.hpp"
27 
28 namespace roccv {
30  // The data type of the tensor.
32 
33  // Location of the tensor's underlying data.
35 
36  // The shape of the tensor.
38 
39  // Distance in bytes between each element of a given dimension.
40  std::array<int64_t, ROCCV_TENSOR_MAX_RANK> strides;
41 };
42 } // namespace roccv
Supported data types for use with the Tensor utilities.
Definition: data_type.hpp:33
TensorShape class.
Definition: tensor_shape.hpp:34
Definition: strided_data_wrap.hpp:33
Definition: tensor_requirements.hpp:29
TensorShape shape
Definition: tensor_requirements.hpp:37
DataType dtype
Definition: tensor_requirements.hpp:31
eDeviceType device
Definition: tensor_requirements.hpp:34
std::array< int64_t, ROCCV_TENSOR_MAX_RANK > strides
Definition: tensor_requirements.hpp:40
eDeviceType
Describes the device type. Used to determine where Tensor data should be allocated and whether operat...
Definition: util_enums.h:69