Function Usage

Image processing algorithms, tensor Subtract algorithm, supporting float16, float32, and uint8 data types. Asynchronous calling is supported. The inplace operation is not supported.

It is supported by the Atlas inference product and Atlas 200I/500 A2 inference product.

For the Atlas 200I/500 A2 inference product, preloading is supported (see Example of the Preloading File of the Initialization Operator).

The following conditions must be met:

The input and output tensors must be on the device or DVPP side, and the parameters (stream and data memory) must be on the same device.
For synchronization, the device where the data memory is located must be the same as the initialized device.
Handle the issue of out-of-range data type if any.
The input and output parameters cannot exceed four dimensions, and must match the tensor shapes and types.
For the Atlas inference product, when the data type of an input tensor is float32 or float16 and the size is greater than 1080p (1920 x 1080), the compute performance is better than that of cv::subtract on the CPU.
For the Atlas 200I/500 A2 inference product, when the input size is greater than 720p (1280 x 720), the compute performance is better than that of cv::subtract on the CPU.

Prototype

APP_ERROR Subtract(const Tensor &src1, const Tensor &src2, Tensor &dst, AscendStream &stream = AscendStream::DefaultStream());

Parameters

Parameter	Input/Output	Description
src1	Input	Tensor class, minuend, input tensor, supporting float16, float32, and uint8 data types.
src2	Input	Tensor class, subtrahend, input tensor, supporting float16, float32, and uint8 data types. When the data type is uint8, the element in the corresponding position of src2 cannot be greater than the element in src1.
dst	Output	Tensor class, output tensor, supporting float16, float32, and uint8 data types. An empty tensor can be passed. If dst is not an empty tensor, call Tensor.Malloc() to allocate memory in advance.
stream	Input	AscendStream type. The default value is AscendStream::DefaultStream(). When the parameter value is the default value, the API calling is a synchronous operation. In other cases, the API calling is an asynchronous operation.

Response Parameters

Data Structure	Description
APP_ERROR	For details about the returned error codes, see APP_ERROR Description.