acldvppAdjustSaturation

Applicability

Function Usage

• Description: adjusts the image saturation.
• Formula:

  out = self * factor + (self->Y8) * (1-factor)

Prototype

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

• First-phase API:

  1	acldvppStatus acldvppAdjustSaturationGetWorkspaceSize(const aclTensor *self, float factor, aclTensor *out, uint64_t *workspaceSize, aclOpExecutor **executor)

• Second-phase API:

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

acldvppAdjustSaturationGetWorkspaceSize

• 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).
  • factor: saturation adjustment coefficient. The value of dataType can be FLOAT. The value of factor can be greater than 0.
  • 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 UINT8 or FLOAT, non-contiguous tensors are not supported, and the values of dataType, 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.

acldvppAdjustSaturation

• 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 acldvppAdjustSaturationGetWorkspaceSize.
  • executor: op executor, which contains the operator computation process and is the same as the executor of the acldvppAdjustSaturationGetWorkspaceSize 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.

If the value of factor is a decimal and dataType of self and out is UINT8, the maximum difference of a single pixel value is ±1 compared with that of the third-party software Torchvision.