2D Convolution

group NVCV_C_ALGORITHM_CONV2D

Functions

NVCVStatus cvcudaConv2DCreate(NVCVOperatorHandle *handle)

Constructs an instance of the Conv2D.

Parameters

handle[out] Where the operator instance handle will be written to.

  • Must not be NULL.

Return values
  • NVCV_ERROR_INVALID_ARGUMENT – Handle is null.

  • NVCV_ERROR_OUT_OF_MEMORY – Not enough memory to create the operator.

  • NVCV_SUCCESS – Operation executed successfully.

NVCVStatus cvcudaConv2DVarShapeSubmit(NVCVOperatorHandle handle, cudaStream_t stream, NVCVImageBatchHandle in, NVCVImageBatchHandle out, NVCVImageBatchHandle kernel, NVCVTensorHandle kernelAnchor, NVCVBorderType borderMode)

Executes the Conv2D operation on the given cuda stream. This operation does not wait for completion.

Limitations:

Input: Data Layout: [kNHWC, kHWC] Channels: [1, 3, 4]

Data Type

Allowed

8bit Unsigned

Yes

8bit Signed

No

16bit Unsigned

Yes

16bit Signed

Yes

32bit Unsigned

No

32bit Signed

Yes

32bit Float

Yes

64bit Float

No

Output: Data Layout: [kNHWC, kHWC] Channels: [1, 3, 4]

Data Type

Allowed

8bit Unsigned

Yes

8bit Signed

No

16bit Unsigned

Yes

16bit Signed

Yes

32bit Unsigned

No

32bit Signed

Yes

32bit Float

Yes

64bit Float

No

Input/Output dependency

 Property      |  Input == Output
-------------- | -------------
 Data Layout   | Yes
 Data Type     | Yes
 Number        | Yes
 Channels      | Yes
 Width         | Yes
 Height        | Yes

Parameters
  • handle[in] Handle to the operator.

    • Must not be NULL.

  • stream[in] Handle to a valid CUDA stream.

  • in[in] Input tensor.

  • out[out] Output tensor.

  • kernel[in] Convolution kernels (one for each batch image) to be used. Each image width and height correspond to the kernel width and height.

    • Must be of pixel type NVCV_DATA_TYPE_F32

  • kernelAnchor[in] 1D Tensor with the anchor of each kernel (one for each batch image). The anchor (x, y) indicates the relative position of a filtered point within the kernel. (-1, -1) means that the anchor is at the kernel center.

    • Must be of pixel type NVCV_DATA_TYPE_2S32

  • borderMode[in] Border mode to be used when accessing elements outside, cf. NVCVBorderType.

Return values
  • NVCV_ERROR_INVALID_ARGUMENT – Some parameter is outside valid range.

  • NVCV_ERROR_INTERNAL – Internal error in the operator, invalid types passed in.

  • NVCV_SUCCESS – Operation executed successfully.