acldvppNormalize

Applicability

Function Usage

• Description: normalizes images by subtracting the mean value and then dividing the result by the standard deviation. The mean value and standard deviation are specified by users.
• Formula:

  out = (self - mean) / std

Prototype

Each operator has two-phase API calls. First, acldvppNormalizeGetWorkspaceSize is called to calculate the required workspace size based on the computation process. Then, acldvppNormalize is called to perform computation. The two-phase APIs are as follows:

• First-phase API:

  1	acldvppStatus acldvppNormalizeGetWorkspaceSize(const aclTensor* self, const aclFloatArray* mean, const aclFloatArray* std, aclTensor* out, uint64_t* workspaceSize, aclOpExecutor** executor)

• Second-phase API:

  1	acldvppStatus acldvppNormalize(void* workspace, uint64_t workspaceSize, aclOpExecutor* executor, aclrtStream stream)

acldvppNormalizeGetWorkspaceSize

• Parameters:
  • self: input tensor of the operator, which is of the aclTensor type created by calling aclCreateTensor (the tensor data is stored on the device). The value of dataType of the input tensor can be UINT8 or FLOAT, the value of Format can be NCHW or NHWC, and non-contiguous tensors are not supported. The value of N can be 1 or left empty, and the value of C can be 1 or 3 (1: input GRAY image; 3: input RGB image).
  • mean: mean value, which is of the aclFloatArray type created by calling aclCreateFloatArray (the mean value data is stored on the host and the value of dataType is FLOAT). The value of the input parameter size of the API must be the same as the size of the C axis.
  • std: standard deviation, which is of the aclFloatArray type created by calling aclCreateFloatArray (the standard deviation data is stored on the host and the value of dataType is FLOAT). The value of the input parameter size of the API must be the same as the size of the C axis.
  • out: output tensor of the operator, which is of the aclTensor type created by calling aclCreateTensor (the tensor data is stored on the device). The value of dataType of the output tensor can be FLOAT, non-contiguous tensors are not supported, and the values of Format and Shape must be the same as those of self.
  • workspaceSize: size of the workspace to be allocated on the device.
  • executor: operator executor, containing the operator computation process.
• Returns:

  acldvppStatus status code. For details, see acldvpp Return Codes.

acldvppNormalize

• Parameters:
  • workspace: address of the device memory allocated by calling aclrtMalloc. The size of the device memory is specified by workspaceSize.
  • workspaceSize: The value must be the same as that obtained by calling acldvppNormalizeGetWorkspaceSize.
  • executor: op executor, which contains the operator computation process and is the same as the executor of the acldvppNormalizeGetWorkspaceSize API.
  • stream: stream for executing a task, which can be a created stream for saving resources or newly created by calling aclrtCreateStream.
• Returns:

  acldvppStatus status code. For details, see acldvpp Return Codes.

Constraints

The supported image resolution ranges from 6 x 4 to 4096 x 8192.