Random Resized Crop

group Random Resized Crop

Unnamed Group

NVCVStatus cvcudaRandomResizedCropSubmit(NVCVOperatorHandle handle, cudaStream_t stream, NVCVTensorHandle in, NVCVTensorHandle out, const NVCVInterpolationType interpolation)

Executes the random resized crop operation on the given cuda stream. This operation does not wait for completion.

Limitations:

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

Data Type

Allowed

8bit Unsigned

Yes

8bit Signed

No

16bit Unsigned

Yes

16bit Signed

Yes

32bit Unsigned

No

32bit Signed

No

16bit Float

No

32bit Float

Yes

64bit Float

No

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

Data Type

Allowed

8bit Unsigned

Yes

8bit Signed

No

16bit Unsigned

Yes

16bit Signed

Yes

32bit Unsigned

No

32bit Signed

No

16bit Float

No

32bit Float

Yes

64bit Float

No

Input/Output dependency 

 Property      |  Input == Output
-------------- | -------------
 Data Layout   | Yes
 Data Type     | Yes
 Number        | Yes
 Channels      | Yes
 Width         | No
 Height        | No

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.

  • interpolation – [in] Interpolation method to be used, see NVCVInterpolationType for more details.

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.

NVCVStatus cvcudaRandomResizedCropVarShapeSubmit(NVCVOperatorHandle handle, cudaStream_t stream, NVCVImageBatchHandle in, NVCVImageBatchHandle out, const NVCVInterpolationType interpolation)

Functions

NVCVStatus cvcudaRandomResizedCropCreate(NVCVOperatorHandle *handle, double minScale, double maxScale, double minRatio, double maxRatio, int32_t maxBatchSize, uint32_t seed)

Constructs an instance of the random resized crop.

Parameters:

  • handle – [out] Where the image instance handle will be written to.

    • Must not be NULL.

  • minScale – [in] Lower bound for the random area of the crop, before resizing. The scale is defined with respect to the area of the original image.

    • Positive value.

  • maxScale – [in] Upper bound for the random area of the crop, before resizing. The scale is defined with respect to the area of the original image.

    • Positive value.

  • minRatio – [in] Lower bound for the random aspect ratio of the crop, before resizing.

    • Positive value.

  • maxRatio – [in] Upper bound for the random aspect ratio of the crop, before resizing.

    • Positive value.

  • maxBatchSize – [in] The maximum batch size that will be used by the operator.

    • Positive value.

  • seed – [in] The random seed that will be used by the operator. Pass 0 to use std::random_device.

    • Positive value.

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.