module onnxrt.ops_cpu.op_grid_sample_#

Short summary#

module mlprodict.onnxrt.ops_cpu.op_grid_sample_

Implements runtime for operator GridSample. The code is inspired from pool.cc in onnxruntime.

source on GitHub

Classes#

class

truncated documentation

GridSampleDouble

Implements float runtime for operator GridSample. The code is inspired from pool.cc …

GridSampleFloat

Implements float runtime for operator GridSample. The code is inspired from pool.cc …

Documentation#

Implements runtime for operator GridSample. The code is inspired from pool.cc in onnxruntime.

class mlprodict.onnxrt.ops_cpu.op_grid_sample_.GridSampleDouble(self: mlprodict.onnxrt.ops_cpu.op_grid_sample_.GridSampleDouble)#

Bases: pybind11_object

Implements float runtime for operator GridSample. The code is inspired from pool.cc in onnxruntime. Supports double only.

__init__(self: mlprodict.onnxrt.ops_cpu.op_grid_sample_.GridSampleDouble) → None#
compute(self: mlprodict.onnxrt.ops_cpu.op_grid_sample_.GridSampleDouble, arg0: numpy.ndarray[numpy.float64], arg1: numpy.ndarray[numpy.float64]) → numpy.ndarray[numpy.float64]#

Computes the output for operator GridSample.

init(self: mlprodict.onnxrt.ops_cpu.op_grid_sample_.GridSampleDouble, arg0: int, arg1: str, arg2: str) → None#

Initializes the runtime with the ONNX attributes.

class mlprodict.onnxrt.ops_cpu.op_grid_sample_.GridSampleFloat(self: mlprodict.onnxrt.ops_cpu.op_grid_sample_.GridSampleFloat)#

Bases: pybind11_object

Implements float runtime for operator GridSample. The code is inspired from pool.cc in onnxruntime. Supports float only.

__init__(self: mlprodict.onnxrt.ops_cpu.op_grid_sample_.GridSampleFloat) → None#
compute(self: mlprodict.onnxrt.ops_cpu.op_grid_sample_.GridSampleFloat, arg0: numpy.ndarray[numpy.float32], arg1: numpy.ndarray[numpy.float32]) → numpy.ndarray[numpy.float32]#

Computes the output for operator GridSample.

init(self: mlprodict.onnxrt.ops_cpu.op_grid_sample_.GridSampleFloat, arg0: int, arg1: str, arg2: str) → None#

Initializes the runtime with the ONNX attributes.