module onnxrt.ops_cpu.op_conv_#

Short summary#

module mlprodict.onnxrt.ops_cpu.op_conv_

Implements runtime for operator Conv. The code is inspired from conv.cc in onnxruntime.

source on GitHub

Classes#

class

truncated documentation

ConvDouble

Implements float runtime for operator Conv. The code is inspired from conv.cc …

ConvFloat

Implements float runtime for operator Conv. The code is inspired from conv.cc …

Documentation#

Implements runtime for operator Conv. The code is inspired from conv.cc in onnxruntime.

class mlprodict.onnxrt.ops_cpu.op_conv_.ConvDouble(self: mlprodict.onnxrt.ops_cpu.op_conv_.ConvDouble)#

Bases: pybind11_object

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

__init__(self: mlprodict.onnxrt.ops_cpu.op_conv_.ConvDouble) → None#
compute(self: mlprodict.onnxrt.ops_cpu.op_conv_.ConvDouble, arg0: numpy.ndarray[numpy.float64], arg1: numpy.ndarray[numpy.float64], arg2: numpy.ndarray[numpy.float64]) → numpy.ndarray[numpy.float64]#

Computes the output for operator Conv.

init(self: mlprodict.onnxrt.ops_cpu.op_conv_.ConvDouble, arg0: str, arg1: numpy.ndarray[numpy.int64], arg2: int, arg3: numpy.ndarray[numpy.int64], arg4: numpy.ndarray[numpy.int64], arg5: numpy.ndarray[numpy.int64]) → None#

Initializes the runtime with the ONNX attributes.

class mlprodict.onnxrt.ops_cpu.op_conv_.ConvFloat(self: mlprodict.onnxrt.ops_cpu.op_conv_.ConvFloat)#

Bases: pybind11_object

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

__init__(self: mlprodict.onnxrt.ops_cpu.op_conv_.ConvFloat) → None#
compute(self: mlprodict.onnxrt.ops_cpu.op_conv_.ConvFloat, arg0: numpy.ndarray[numpy.float32], arg1: numpy.ndarray[numpy.float32], arg2: numpy.ndarray[numpy.float32]) → numpy.ndarray[numpy.float32]#

Computes the output for operator Conv.

init(self: mlprodict.onnxrt.ops_cpu.op_conv_.ConvFloat, arg0: str, arg1: numpy.ndarray[numpy.int64], arg2: int, arg3: numpy.ndarray[numpy.int64], arg4: numpy.ndarray[numpy.int64], arg5: numpy.ndarray[numpy.int64]) → None#

Initializes the runtime with the ONNX attributes.