///
/// Copyright (c) 2021-2023 Arm Limited.
///
/// SPDX-License-Identifier: MIT
///
/// Permission is hereby granted, free of charge, to any person obtaining a copy
/// of this software and associated documentation files (the "Software"), to
/// deal in the Software without restriction, including without limitation the
/// rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
/// sell copies of the Software, and to permit persons to whom the Software is
/// furnished to do so, subject to the following conditions:
///
/// The above copyright notice and this permission notice shall be included in all
/// copies or substantial portions of the Software.
///
/// THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
/// IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
/// FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
/// AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
/// LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
/// OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
/// SOFTWARE.
///
namespace arm_compute
{
/**
@page operators_list Supported Operators
@tableofcontents
@section S9_1_operators_list Supported Operators
Compute Library supports operators that are listed in below table.
Compute Library supports a wide list of data-types, information can been directly found in the documentation of each kernel/function.
The main data-types that the Machine Learning functions support are the following:
Function
| Description
| Equivalent Android NNAPI Op
| Backends
| Data Layouts
| Data Types
|
ActivationLayer
| Function to simulate an activation layer with the specified activation function.
|
- ANEURALNETWORKS_ELU
- ANEURALNETWORKS_HARD_SWISH
- ANEURALNETWORKS_LOGISTIC
- ANEURALNETWORKS_RELU
- ANEURALNETWORKS_RELU1
- ANEURALNETWORKS_RELU6
- ANEURALNETWORKS_TANH
| NEActivationLayer
|
|
src | dst
|
---|
QASYMM8 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED
| QSYMM16 | QSYMM16
| F16 | F16
| F32 | F32
|
|
CLActivationLayer
|
|
src | dst
|
---|
QASYMM8 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED
| QSYMM16 | QSYMM16
| F16 | F16
| F32 | F32
|
|
AddMulAdd
| Performs a fused Add + Mul + Add [+ Relu-based-Activation] operation.
|
| NEAddMulAdd
|
|
input1 | input2 | bn_mul | bn_add | add_output | final_output
|
---|
QASYMM8 | QASYMM8 | QASYMM8 | QASYMM8 | QASYMM8 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED | QASYMM8_SIGNED | QASYMM8_SIGNED | QASYMM8_SIGNED | QASYMM8_SIGNED
| F16 | F16 | F16 | F16 | F16 | F16
| F32 | F32 | F32 | F32 | F32 | F32
|
|
ArgMinMaxLayer
| Function to calculate the index of the minimum or maximum values in a tensor based on an axis.
|
- ANEURALNETWORKS_ARGMAX
- ANEURALNETWORKS_ARGMIN
| NEArgMinMaxLayer
|
|
src | dst
|
---|
QASYMM8 | U32, S32
| QASYMM8_SIGNED | U32, S32
| S32 | U32, S32, S64
| F16 | U32, S32
| F32 | U32, S32
|
|
CLArgMinMaxLayer
|
|
src | dst
|
---|
QASYMM8 | U32, S32
| QASYMM8_SIGNED | U32, S32
| S32 | U32, S32
| F16 | U32, S32
| F32 | U32, S32
|
|
ArithmeticAddition
| Function to add 2 tensors.
|
| NEArithmeticAddition
|
|
src0 | src1 | dst
|
---|
QASYMM8 | QASYMM8 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED | QASYMM8_SIGNED
| QSYMM16 | QSYMM16 | QASYMM16
| QSYMM16 | QSYMM16 | S32
| U8 | U8 | U8
| S16 | S16 | S16
| S32 | S32 | S32
| F16 | F16 | F16
| F32 | F32 | F32
|
|
ArithmeticSubtraction
| Function to substract 2 tensors.
|
| NEArithmeticSubtraction
|
|
src0 | src1 | dst
|
---|
QASYMM8 | QASYMM8 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED | QASYMM8_SIGNED
| QSYMM16 | QSYMM16 | QASYMM16
| QSYMM16 | QSYMM16 | S32
| U8 | U8 | U8
| S16 | S16 | S16
| S32 | S32 | S32
| F16 | F16 | F16
| F32 | F32 | F32
|
|
BatchNormalizationLayer
| Function to perform batch normalization.
|
| NEBatchNormalizationLayer
|
|
|
CLBatchNormalizationLayer
|
|
|
BatchToSpaceLayer
| Batch to space transformation.
|
- ANEURALNETWORKS_BATCH_TO_SPACE_ND
| NEBatchToSpaceLayer
|
|
|
CLBatchToSpaceLayer
|
|
|
BitwiseAnd
| Function to perform bitwise AND between 2 tensors.
|
- ANEURALNETWORKS_LOGICAL_AND
| NEBitwiseAnd
|
|
|
CLBitwiseAnd
|
|
|
BitwiseNot
| Function to perform bitwise NOT.
|
- ANEURALNETWORKS_LOGICAL_NOT
| NEBitwiseNot
|
|
|
CLBitwiseNot
|
|
|
BitwiseOr
| Function to perform bitwise OR between 2 tensors.
|
- ANEURALNETWORKS_LOGICAL_OR
| NEBitwiseOr
|
|
|
CLBitwiseOr
|
|
|
BitwiseXor
| Function to perform bitwise XOR between 2 tensors.
|
| NEBitwiseXor
|
|
|
CLBitwiseXor
|
|
|
BoundingBoxTransform
| Transform proposal bounding boxes to target bounding box using bounding box deltas.
|
| NEBoundingBoxTransform
|
|
src0 | src1 | dst
|
---|
QASYMM16 | QASYMM8 | QASYMM16
| F16 | F16 | F16
| F32 | F32 | F32
|
|
CLBoundingBoxTransform
|
|
src0 | src1 | dst
|
---|
QASYMM16 | QASYMM8 | QASYMM16
| F16 | F16 | F16
| F32 | F32 | F32
|
|
Cast
| Function to cast a tensor.
|
| NECast
|
|
src | dst
|
---|
QASYMM8_SIGNED | S16, S32, F32, F16
| QASYMM8 | U16, S16, S32, F32, F16
| U8 | U16, S16, S32, F32, F16
| U16 | U8, U32
| S16 | QASYMM8_SIGNED, U8, S32
| F16 | QASYMM8_SIGNED, QASYMM8, F32, S32, U8
| S32 | QASYMM8_SIGNED, QASYMM8, F16, F32, U8
| F32 | QASYMM8_SIGNED, QASYMM8, BFLOAT16, F16, S32, U8
|
|
CLCast
|
|
src | dst
|
---|
U8 | S8, U16, S16, U32, S32, F16, F32
| S8 | U8, U16, S16, U32, S32, F16, F32
| U16 | U8, S8, S16, U32, S32, F16, F32
| S16 | U8, S8, U16, U32, S32, F16, F32
| U32 | U8, S8, U16, S16, S32, F16, F32
| S32 | U8, S8, U16, S16, U32, F16, F32
| U64 | U8, S8, U16, S16, U32, S32, F16, F32
| S64 | U8, S8, U16, S16, U32, S32, F16, F32
| F16 | U8, S8, U16, S16, S32, U32, F32
| F32 | U8, S8, U16, S16, S32, U32, F16
|
|
ChannelShuffleLayer
| Function to shuffle the channels of the input tensor.
|
- ANEURALNETWORKS_CHANNEL_SHUFFLE
| NEChannelShuffleLayer
|
|
|
CLChannelShuffleLayer
|
|
|
Comparison
| Function to compare 2 tensors.
|
- ANEURALNETWORKS_EQUAL
- ANEURALNETWORKS_GREATER
- ANEURALNETWORKS_GREATER_EQUAL
- ANEURALNETWORKS_LESS
- ANEURALNETWORKS_LESS_EQUAL
- ANEURALNETWORKS_NOT_EQUAL
| CLComparison
|
|
|
ConcatenateLayer
| Function to concatenate tensors along a given axis.
|
- ANEURALNETWORKS_CONCATENATION
| NEConcatenateLayer
|
|
src | dst
|
---|
QASYMM8 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED
| F16 | F16
| F32 | F32
|
|
CLConcatenateLayer
|
|
src | dst
|
---|
QASYMM8 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED
| F16 | F16
| F32 | F32
|
|
ConvertFullyConnectedWeights
| Function to transpose the weights for the fully connected layer.
|
| NEConvertFullyConnectedWeights
|
|
|
CLConvertFullyConnectedWeights
|
|
|
ConvolutionLayer
| Function to compute a convolution layer.
|
| NEConvolutionLayer
|
|
src0 | src1 | src2 | dst
|
---|
F16 | F16 | F16 | F16
| F32 | F32 | F32 | F32
| QASYMM8 | QASYMM8 | S32 | QASYMM8
| QASYMM8 | QSYMM8_PER_CHANNEL | S32 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED | S32 | QASYMM8_SIGNED
| QASYMM8_SIGNED | QSYMM8_PER_CHANNEL | S32 | QASYMM8_SIGNED
|
|
CLConvolutionLayer
|
|
src0 | src1 | src2 | dst
|
---|
F16 | F16 | F16 | F16
| F32 | F32 | F32 | F32
| QASYMM8 | QASYMM8 | S32 | QASYMM8
| QASYMM8 | QSYMM8_PER_CHANNEL | S32 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED | S32 | QASYMM8_SIGNED
| QASYMM8_SIGNED | QSYMM8_PER_CHANNEL | S32 | QASYMM8_SIGNED
|
|
Conv3D
| Function to compute a 3d convolution layer.
|
| NEConv3D
|
|
src0 | src1 | src2 | dst
|
---|
F16 | F16 | F16 | F16
| F32 | F32 | F32 | F32
| QASYMM8 | QASYMM8 | S32 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED | S32 | QASYMM8_SIGNED
|
|
CLConv3D
|
|
src0 | src1 | src2 | dst
|
---|
F16 | F16 | F16 | F16
| F32 | F32 | F32 | F32
| QASYMM8 | QASYMM8 | S32 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED | S32 | QASYMM8_SIGNED
|
|
Copy
| Function to copy a tensor.
|
| NECopy
|
|
|
CLCopy
|
|
|
Crop
| Performs a copy of input tensor to the output tensor.
|
| CLCrop
|
|
|
CropResize
| Function to perform cropping and resizing.
|
| NECropResize
|
|
src0 | src1 | src2 | dst
|
---|
All | F32 | F32 | F32
|
|
CLCropResize
|
|
src0 | src1 | src2 | dst
|
---|
All | F32 | F32 | F32
|
|
DeconvolutionLayer
| Function to compute a deconvolution or transpose convolution.
|
- ANEURALNETWORKS_TRANSPOSE_CONV_2D
| NEDeconvolutionLayer
|
|
src0 | src1 | src2 | dst
|
---|
F16 | F16 | F16 | F16
| F32 | F32 | F32 | F32
| QASYMM8 | QASYMM8 | S32 | QASYMM8
| QASYMM8 | QSYMM8_PER_CHANNEL | S32 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED | S32 | QASYMM8_SIGNED
| QASYMM8_SIGNED | QSYMM8_PER_CHANNEL | S32 | QASYMM8_SIGNED
|
|
CLDeconvolutionLayer
|
|
src0 | src1 | src2 | dst
|
---|
F16 | F16 | F16 | F16
| F32 | F32 | F32 | F32
| QASYMM8 | QASYMM8 | S32 | QASYMM8
| QASYMM8 | QSYMM8_PER_CHANNEL | S32 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED | S32 | QASYMM8_SIGNED
| QASYMM8_SIGNED | QSYMM8_PER_CHANNEL | S32 | QASYMM8_SIGNED
|
|
DeconvolutionLayerUpsample
| Function to execute deconvolution upsample on OpenCL.
|
- ANEURALNETWORKS_TRANSPOSE_CONV_2D
| CLDeconvolutionLayerUpsample
|
|
|
DepthConvertLayer
| Performs a down-scaling depth conversion.
|
| NEDepthConvertLayer
|
|
src | dst
|
---|
QASYMM8 | F16, F32
| U8 | U16, S16, S32
| U16 | U8, U32
| S16 | U8, S32
| BFLOAT16 | F32
| F16 | QASYMM8, F32
| F32 | QASYMM8, F16, BFLOAT16
|
|
CLDepthConvertLayer
|
|
src | dst
|
---|
U8 | S8, U16, S16, U32, S32, F16, F32
| U16 | U8, S8, S16, U32, S32, F16, F32
| S16 | U8, S8, U16, U32, S32, F16, F32
| U32 | U8, S8, U16, S16, S32, F16, F32
| S32 | U8, S8, U16, S16, U32, F16, F32
| F16 | U8, S8, U16, S16, U32, F32
| F32 | U8, S8, U16, S16, U32, F16
|
|
DepthToSpaceLayer
| Depth to Space transformation.
|
- ANEURALNETWORKS_DEPTH_TO_SPACE
| NEDepthToSpaceLayer
|
|
|
CLDepthToSpaceLayer
|
|
|
DepthwiseConvolutionLayer
| Function to perform depthwise separable convolution.
|
- ANEURALNETWORKS_DEPTHWISE_CONV_2D
| NEDepthwiseConvolutionLayer
|
|
src0 | src1 | src2 | dst
|
---|
F16 | F16 | F16 | F16
| F32 | F32 | F32 | F32
| QASYMM8 | QASYMM8 | S32 | QASYMM8
| QASYMM8 | QSYMM8_PER_CHANNEL | S32 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED | S32 | QASYMM8_SIGNED
| QASYMM8_SIGNED | QSYMM8_PER_CHANNEL | S32 | QASYMM8_SIGNED
|
|
CLDepthwiseConvolutionLayer
|
|
src0 | src1 | src2 | dst
|
---|
F16 | F16 | F16 | F16
| F32 | F32 | F32 | F32
| QASYMM8 | QASYMM8 | S32 | QASYMM8
| QASYMM8 | QSYMM8_PER_CHANNEL | S32 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED | S32 | QASYMM8_SIGNED
| QASYMM8_SIGNED | QSYMM8_PER_CHANNEL | S32 | QASYMM8_SIGNED
|
|
DequantizationLayer
| Function to dequantize the values in a tensor.
|
- ANEURALNETWORKS_DEQUANTIZE
| NEDequantizationLayer
|
|
src | dst
|
---|
QASYMM8 | F16, F32
| QASYMM8_SIGNED | F16, F32
| QSYMM8_PER_CHANNEL | F16, F32
| QSYMM8 | F16, F32
| QSYMM16 | F16, F32
|
|
CLDequantizationLayer
|
|
src | dst
|
---|
QASYMM8 | F16, F32
| QASYMM8_SIGNED | F16, F32
| QSYMM8_PER_CHANNEL | F16, F32
| QSYMM8 | F16, F32
| QSYMM16 | F16, F32
|
|
DetectionPostProcessLayer
| Function to generate the detection output based on center size encoded boxes, class prediction and anchors by doing non maximum suppression (NMS).
|
- ANEURALNETWORKS_DETECTION_POSTPROCESSING
| NEDetectionPostProcessLayer
|
|
src0 - src2 | dst0 - dst3
|
---|
QASYMM8 | F32
| QASYMM8_SIGNED | F32
| F32 | F32
|
|
DirectConvolutionLayer
| Function to compute direct convolution.
|
| NEDirectConvolutionLayer
|
|
src0 | src1 | src2 | dst
|
---|
F16 | F16 | F16 | F16
| F32 | F32 | F32 | F32
|
|
CLDirectConvolutionLayer
|
|
src0 | src1 | src2 | dst
|
---|
F16 | F16 | F16 | F16
| F32 | F32 | F32 | F32
| QASYMM8 | QASYMM8 | S32 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED | S32 | QASYMM8_SIGNED
|
|
DirectDeconvolutionLayer
| Function to run the deconvolution layer.
|
- ANEURALNETWORKS_TRANSPOSE_CONV_2D
| CLDirectDeconvolutionLayer
|
|
src0 | src1 | src2 | dst
|
---|
F16 | F16 | F16 | F16
| F32 | F32 | F32 | F32
| QASYMM8 | QASYMM8 | S32 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED | S32 | QASYMM8_SIGNED
| QASYMM8 | QSYMM8_PER_CHANNEL | S32 | QASYMM8
| QASYMM8_SIGNED | QSYMM8_PER_CHANNEL | S32 | QASYMM8_SIGNED
|
|
ElementwiseOperations
| Function to perform in Cpu: - Div - Max - Min - Pow - SquaredDiff - Comparisons (Equal, greater, greater_equal, less, less_equal, not_equal) Function to perform in CL: - Add - Sub - Div - Max - Min - Pow - SquaredDiff
|
- ANEURALNETWORKS_MAXIMUM
- ANEURALNETWORKS_MINIMUM
- ANEURALNETWORKS_POW
- ANEURALNETWORKS_DIV
- ANEURALNETWORKS_ADD
- ANEURALNETWORKS_SUB
- ANEURALNETWORKS_EQUAL
- ANEURALNETWORKS_GREATER
- ANEURALNETWORKS_GREATER_EQUAL
- ANEURALNETWORKS_LESS
- ANEURALNETWORKS_LESS_EQUAL
- ANEURALNETWORKS_NOT_EQUAL
| NEElementwiseMax
|
|
src0 | src1 | dst
|
---|
QASYMM8 | QASYMM8 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED | QASYMM8_SIGNED
| S32 | S32 | S32
| S16 | S16 | S16
| F16 | F16 | F16
| F32 | F32 | F32
|
|
NEElementwiseMin
|
|
src0 | src1 | dst
|
---|
QASYMM8 | QASYMM8 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED | QASYMM8_SIGNED
| S32 | S32 | S32
| S16 | S16 | S16
| F16 | F16 | F16
| F32 | F32 | F32
|
|
NEElementwiseSquaredDiff
|
|
src0 | src1 | dst
|
---|
QASYMM8 | QASYMM8 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED | QASYMM8_SIGNED
| S32 | S32 | S32
| S16 | S16 | S16
| F16 | F16 | F16
| F32 | F32 | F32
|
|
NEElementwiseDivision
|
|
src0 | src1 | dst
|
---|
F16 | F16 | F16
| F32 | F32 | F32
|
|
NEElementwisePower
|
|
src0 | src1 | dst
|
---|
F16 | F16 | F16
| F32 | F32 | F32
|
|
NEElementwiseComparison
|
|
src0 | src1 | dst
|
---|
QASYMM8 | QASYMM8 | U8
| QASYMM8_SIGNED | QASYMM8_SIGNED | U8
| S32 | S32 | U8
| U8 | U8 | U8
| S16 | S16 | U8
| F16 | F16 | U8
| F32 | F32 | U8
|
|
CLArithmeticAddition
|
|
src0 | src1 | dst
|
---|
QASYMM8 | QASYMM8 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED | QASYMM8_SIGNED
| QSYMM16 | QSYMM16 | QASYMM16
| U8 | U8 | U8
| U8 | U8 | S16
| U8 | S16 | S16
| S16 | U8 | S16
| S16 | S16 | S16
| S32 | S32 | S32
| F16 | F16 | F16
| F32 | F32 | F32
|
|
CLArithmeticSubtraction
|
|
src0 | src1 | dst
|
---|
QASYMM8 | QASYMM8 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED | QASYMM8_SIGNED
| QSYMM16 | QSYMM16 | QASYMM16
| U8 | U8 | U8
| U8 | U8 | S16
| U8 | S16 | S16
| S16 | U8 | S16
| S16 | S16 | S16
| S32 | S32 | S32
| F16 | F16 | F16
| F32 | F32 | F32
|
|
CLArithmeticDivision
|
|
src0 | src1 | dst
|
---|
F16 | F16 | F16
| F32 | F32 | F32
|
|
CLElementwiseMax
|
|
src0 | src1 | dst
|
---|
QASYMM8 | QASYMM8 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED | QASYMM8_SIGNED
| QSYMM16 | QSYMM16 | QASYMM16
| U8 | U8 | U8
| S16 | S16 | S16
| S32 | S32 | S32
| U32 | U32 | U32
| F16 | F16 | F16
| F32 | F32 | F32
|
|
CLElementwiseMin
|
|
src0 | src1 | dst
|
---|
QASYMM8 | QASYMM8 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED | QASYMM8_SIGNED
| QSYMM16 | QSYMM16 | QASYMM16
| U8 | U8 | U8
| S16 | S16 | S16
| S32 | S32 | S32
| U32 | U32 | U32
| F16 | F16 | F16
| F32 | F32 | F32
|
|
CLElementwiseSquaredDiff
|
|
src0 | src1 | dst
|
---|
QASYMM8 | QASYMM8 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED | QASYMM8_SIGNED
| QSYMM16 | QSYMM16 | QASYMM16
| U8 | U8 | U8
| S16 | S16 | S16
| F16 | F16 | F16
| F32 | F32 | F32
|
|
CLElementwisePower
|
|
src0 | src1 | dst
|
---|
F16 | F16 | F16
| F32 | F32 | F32
|
|
ElementwiseUnaryLayer
| Function to perform: - Rsqrt - Exp - Neg - Log - Abs - Round - Sin
|
- ANEURALNETWORKS_ABS
- ANEURALNETWORKS_EXP
- ANEURALNETWORKS_LOG
- ANEURALNETWORKS_NEG
- ANEURALNETWORKS_RSQRT
- ANEURALNETWORKS_SIN
| NEElementwiseUnaryLayer
|
|
src | dst
|
---|
F16 | F16
| F32 | F32
| S32 | S32
|
|
CLRsqrtLayer
|
|
|
CLExpLayer
|
|
|
CLNegLayer
|
|
src | dst
|
---|
F16 | F16
| F32 | F32
| S32 | S32
|
|
CLSinLayer
|
|
|
CLLogLayer
|
|
|
CLAbsLayer
|
|
|
CLRoundLayer
|
|
|
FFT1D
| Fast Fourier Transform 1D.
|
| NEFFT1D
|
|
|
CLFFT1D
|
|
|
FFT2D
| Fast Fourier Transform 2D.
|
| NEFFT2D
|
|
|
CLFFT2D
|
|
|
FFTConvolutionLayer
| Fast Fourier Transform Convolution.
|
| NEFFTConvolutionLayer
|
|
|
CLFFTConvolutionLayer
|
|
|
Fill
| Set the values of a tensor with a given value.
|
| NEFill
|
|
|
CLFill
|
|
|
FillBorder
| Function to fill the borders within the XY-planes.
|
| NEFillBorder
|
|
|
FlattenLayer
| Reshape a tensor to be 1D
|
| NEFlattenLayer
|
|
|
CLFlattenLayer
|
|
|
Floor
| Round the value to the lowest number.
|
| NEFloor
|
|
|
CLFloor
|
|
|
FullyConnectedLayer
| Function to perform a fully connected / dense layer.
|
- ANEURALNETWORKS_FULLY_CONNECTED
| NEFullyConnectedLayer
|
|
src0 | src1 | src2 | dst
|
---|
F16 | F16 | F16 | F16
| F32 | F32 | F32 | F32
| QASYMM8 | QASYMM8 | S32 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED | S32 | QASYMM8_SIGNED
|
|
CLFullyConnectedLayer
|
|
src0 | src1 | src2 | dst
|
---|
F16 | F16 | F16 | F16
| F32 | F32 | F32 | F32
| QASYMM8 | QASYMM8 | S32 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED | S32 | QASYMM8_SIGNED
|
|
FuseBatchNormalization
| Function to fuse the batch normalization node to a preceding convolution node.
|
| NEFuseBatchNormalization
|
|
|
CLFuseBatchNormalization
|
|
|
Gather
| Performs the Gather operation along the chosen axis.
|
| NEGather
|
|
|
CLGather
|
|
|
GEMM
| General Matrix Multiplication.
|
| NEGEMM
|
|
src0 | src1 | src2 | dst
|
---|
F32 | F32 | F32 | F32
| F16 | F16 | F16 | F16
| BFLOAT16 | BFLOAT16 | BFLOAT16 | BFLOAT16
|
|
CLGEMM
|
|
src0 | src1 | src2 | dst
|
---|
F32 | F32 | F32 | F32
| F16 | F16 | F16 | F16
|
|
GEMMConv2d
| General Matrix Multiplication.
|
| NEGEMMConv2d
|
|
src0 | src1 | src2 | dst
|
---|
QASYMM8 | QASYMM8 | S32 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED | S32 | QASYMM8_SIGNED
| F16 | F16 | F16 | F16
| F32 | F32 | F32 | F32
| BFLOAT16 | BFLOAT16 | BFLOAT16 | BFLOAT16
|
|
GEMMConvolutionLayer
| General Matrix Multiplication.
|
| NEGEMMConvolutionLayer
|
|
src0 | src1 | src2 | dst
|
---|
F16 | F16 | F16 | F16
| F32 | F32 | F32 | F32
| BFLOAT16 | BFLOAT16 | BFLOAT16 | BFLOAT16
| QASYMM8 | QASYMM8 | S32 | QASYMM8
| QASYMM8 | QSYMM8_PER_CHANNEL | S32 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED | S32 | QASYMM8_SIGNED
| QASYMM8_SIGNED | QSYMM8_PER_CHANNEL | S32 | QASYMM8_SIGNED
|
|
CLGEMMConvolutionLayer
|
|
src0 | src1 | src2 | dst
|
---|
F16 | F16 | F16 | F16
| F32 | F32 | F32 | F32
| QASYMM8 | QASYMM8 | S32 | QASYMM8
| QASYMM8 | QSYMM8_PER_CHANNEL | S32 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED | S32 | QASYMM8_SIGNED
| QASYMM8_SIGNED | QSYMM8_PER_CHANNEL | S32 | QASYMM8_SIGNED
|
|
GEMMDeconvolutionLayer
| General Matrix Multiplication.
|
- ANEURALNETWORKS_TRANSPOSE_CONV_2D
| CLGEMMDeconvolutionLayer
|
|
src0 | src1 | src2 | dst
|
---|
F16 | F16 | F16 | F16
| F32 | F32 | F32 | F32
| QASYMM8 | QASYMM8 | S32 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED | S32 | QASYMM8_SIGNED
|
|
GEMMLowpMatrixMultiplyCore
| General Matrix Multiplication.
|
| NEGEMMLowpMatrixMultiplyCore
|
|
src0 | src1 | src2 | dst
|
---|
QASYMM8 | QASYMM8 | S32 | QASYMM8
| QASYMM8 | QSYMM8_PER_CHANNEL | S32 | QASYMM8
| QASYMM8 | QSYMM8 | S32 | QASYMM8
| QASYMM8 | QASYMM8 | S32 | S32
| QASYMM8 | QSYMM8_PER_CHANNEL | S32 | S32
| QASYMM8 | QSYMM8 | S32 | S32
| QASYMM8_SIGNED | QASYMM8_SIGNED | S32 | QASYMM8_SIGNED
| QASYMM8_SIGNED | QSYMM8_PER_CHANNEL | S32 | QASYMM8_SIGNED
| QASYMM8_SIGNED | QSYMM8 | S32 | QASYMM8_SIGNED
| QASYMM8_SIGNED | QASYMM8_SIGNED | S32 | S32
| QASYMM8_SIGNED | QSYMM8_PER_CHANNEL | S32 | S32
| QASYMM8_SIGNED | QSYMM8 | S32 | S32
|
|
CLGEMMLowpMatrixMultiplyCore
|
|
src0 | src1 | src2 | dst
|
---|
QASYMM8 | QASYMM8 | S32 | QASYMM8
| QASYMM8 | QSYMM8_PER_CHANNEL | S32 | QASYMM8
| QASYMM8 | QSYMM8 | S32 | QASYMM8
| QASYMM8 | QASYMM8 | S32 | S32
| QASYMM8 | QSYMM8_PER_CHANNEL | S32 | S32
| QASYMM8 | QSYMM8 | S32 | S32
| QASYMM8_SIGNED | QASYMM8_SIGNED | S32 | QASYMM8_SIGNED
| QASYMM8_SIGNED | QSYMM8_PER_CHANNEL | S32 | QASYMM8_SIGNED
| QASYMM8_SIGNED | QSYMM8 | S32 | QASYMM8_SIGNED
| QASYMM8_SIGNED | QASYMM8_SIGNED | S32 | S32
| QASYMM8_SIGNED | QSYMM8_PER_CHANNEL | S32 | S32
| QASYMM8_SIGNED | QSYMM8 | S32 | S32
|
|
GEMMLowpOutputStage
| General Matrix Multiplication.
|
| NEGEMMLowpOutputStage
|
|
src0 | src1 | dst
|
---|
S32 | S32 | QASYMM8
| S32 | S32 | QASYMM8_SIGNED
| S32 | S32 | QSYMM16
|
|
CLGEMMLowpOutputStage
|
|
src0 | src1 | dst
|
---|
S32 | S32 | QASYMM8
| S32 | S32 | QASYMM8_SIGNED
| S32 | S32 | QSYMM16
|
|
GenerateProposalsLayer
| Function to generate proposals for a RPN (Region Proposal Network).
|
- ANEURALNETWORKS_GENERATE_PROPOSALS
| NEGenerateProposalsLayer
|
|
src0 | src1 | src2 | dst
|
---|
F16 | F16 | F16 | F16
| F32 | F32 | F32 | F32
| QASYMM8 | QSYMM8 | QSYMM16 | QASYMM8
|
|
CLGenerateProposalsLayer
|
|
src0 | src1 | src2 | dst
|
---|
F16 | F16 | F16 | F16
| F32 | F32 | F32 | F32
| QASYMM8 | QSYMM8 | QSYMM16 | QASYMM8
|
|
InstanceNormalizationLayer
| Function to perform a Instance normalization on a given axis.
|
- ANEURALNETWORKS_INSTANCE_NORMALIZATION
| NEInstanceNormalizationLayer
|
|
|
CLInstanceNormalizationLayer
|
|
|
L2NormalizeLayer
| Function to perform a L2 normalization on a given axis.
|
- ANEURALNETWORKS_L2_NORMALIZATION
| NEL2NormalizeLayer
|
|
|
CLL2NormalizeLayer
|
|
|
Logical
| Function to perform: - Logical AND - Logical OR - Logical NOT
|
| NELogicalAnd
|
|
|
NELogicalOr
|
|
|
NELogicalNot
|
|
|
LogicalAnd
| Function to perform Logical AND.
|
| CLLogicalAnd
|
|
|
LogicalOr
| Function to perform Logical OR.
|
| CLLogicalOr
|
|
|
LogicalNot
| Function to perform Logical NOT.
|
| CLLogicalNot
|
|
|
LSTMLayer
| Function to perform a single time step in a Long Short-Term Memory (LSTM) layer.
|
| NELSTMLayer
|
|
src0 - src13 | dst0 - dst3
|
---|
F16 | F16
| F32 | F32
|
|
CLLSTMLayer
|
|
src0 - src13 | dst0 - dst3
|
---|
F16 | F16
| F32 | F32
|
|
LSTMLayerQuantized
| Function to perform quantized LSTM (Long Short-Term Memory)
|
- ANEURALNETWORKS_QUANTIZED_LSTM
- ANEURALNETWORKS_QUANTIZED_16BIT_LSTM
| NELSTMLayerQuantized
|
|
src0 - src8 | src9 - src12 | src13 | src14 | dst0 | dst1
|
---|
QASYMM8 | S32 | QSYMM16 | QASYMM8 | QSYMM16 | QASYMM8
|
|
CLLSTMLayerQuantized
|
|
src0 - src8 | src9 - src12 | src13 | src14 | dst0 | dst1
|
---|
QASYMM8 | S32 | QSYMM16 | QASYMM8 | QSYMM16 | QASYMM8
|
|
MatMul
| Computes a matrix multiplication in batches.
|
- ANEURALNETWORKS_BATCH_MATMUL
| NEMatMul
|
|
lhs | rhs | dst
|
---|
F32 | F32 | F32
| F16 | F16 | F16
| QASYMM8_SIGNED | QASYMM8_SIGNED | QASYMM8_SIGNED
| QASYMM8 | QASYMM8 | QASYMM8
|
|
CLMatMul
|
|
lhs | rhs | dst
|
---|
F32 | F32 | F32
| F16 | F16 | F16
| QASYMM8_SIGNED | QASYMM8_SIGNED | QASYMM8_SIGNED
| QASYMM8 | QASYMM8 | QASYMM8
|
|
MaxUnpoolingLayer
| Function to perform MaxUnpooling.
|
| NEMaxUnpoolingLayer
|
|
src | dst
|
---|
QASYMM8 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED
| F16 | F16
| F32 | F32
|
|
CLMaxUnpoolingLayer
|
|
src | dst
|
---|
QASYMM8 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED
| F16 | F16
| F32 | F32
|
|
MeanStdDevNormalizationLayer
| Function to execute mean and standard deviation normalization.
|
| NEMeanStdDevNormalizationLayer
|
|
|
CLMeanStdDevNormalizationLayer
|
|
|
NormalizationLayer
| Function to compute normalization layer.
|
- ANEURALNETWORKS_LOCAL_RESPONSE_NORMALIZATION
| NENormalizationLayer
|
|
|
CLNormalizationLayer
|
|
|
NormalizePlanarYUVLayer
| Function to compute normalization planar YUV layer.
|
| CLNormalizePlanarYUVLayer
|
|
src | dst
|
---|
F32 | F32
| F16 | F16
| QASYMM8 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED
|
|
PadLayer
| Function to pad a tensor.
|
- ANEURALNETWORKS_PAD
- ANEURALNETWORKS_PAD_V2
| NEPadLayer
|
|
|
CLPadLayer
|
|
|
Permute
| Function to transpose an ND tensor.
|
- ANEURALNETWORKS_TRANSPOSE
| NEPermute
|
|
|
CLPermute
|
|
|
PixelWiseMultiplication
| Function to perform a multiplication.
|
| NEPixelWiseMultiplication
|
|
src0 | src1 | dst
|
---|
QASYMM8 | QASYMM8 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED | QASYMM8_SIGNED
| QSYMM16 | QSYMM16 | QASYMM16
| QSYMM16 | QSYMM16 | S32
| U8 | U8 | U8
| U8 | U8 | S16
| U8 | S16 | S16
| S16 | U8 | S16
| S16 | S16 | S16
| F16 | F16 | F16
| F32 | S32 | F32
|
|
CLPixelWiseMultiplication
|
|
src0 | src1 | dst
|
---|
QASYMM8 | QASYMM8 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED | QASYMM8_SIGNED
| QSYMM16 | QSYMM16 | QASYMM16
| QSYMM16 | QSYMM16 | S32
| U8 | U8 | U8
| U8 | U8 | S16
| U8 | S16 | S16
| S16 | U8 | S16
| S16 | S16 | S16
| F16 | F16 | F16
| F32 | F32 | F32
| S32 | S32 | S32
|
|
PoolingLayer
| Function to perform pooling with the specified pooling operation.
|
- ANEURALNETWORKS_AVERAGE_POOL_2D
- ANEURALNETWORKS_L2_POOL_2D
- ANEURALNETWORKS_MAX_POOL_2D
| NEPoolingLayer
|
|
src | dst
|
---|
QASYMM8 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED
| F16 | F16
| F32 | F32
|
|
CLPoolingLayer
|
|
src | dst
|
---|
QASYMM8 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED
| F16 | F16
| F32 | F32
|
|
Pooling3dLayer
| Function to perform pooling 3D with the specified pooling operation.
|
| NEPooling3dLayer
|
|
src | dst
|
---|
F16 | F16
| F32 | F32
| QASYMM8 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED
|
|
CLPooling3dLayer
|
|
src | dst
|
---|
F16 | F16
| F32 | F32
| QASYMM8 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED
|
|
PReluLayer
| Function to compute the activation layer with the PRELU activation function.
|
| NEPReluLayer
|
|
src | dst
|
---|
QASYMM8 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED
| F16 | F16
| F32 | F32
|
|
CLPReluLayer
|
|
src | dst
|
---|
QASYMM8 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED
| F16 | F16
| F32 | F32
|
|
PriorBoxLayer
| Function to compute prior boxes and clip.
|
| NEPriorBoxLayer
|
|
|
CLPriorBoxLayer
|
|
|
QLSTMLayer
| Function to perform quantized LSTM (Long Short-Term Memory).
|
- ANEURALNETWORKS_QUANTIZED_LSTM
- ANEURALNETWORKS_QUANTIZED_16BIT_LSTM
| NEQLSTMLayer
|
|
src0 | src1 - src6 | src7 -src9 | src10 | src11 | dst0 | dst1 - dst2
|
---|
QASYMM8_SIGNED | QASYMM8 | S32 | QSYMM16 | QASYMM8_SIGNED | QSYMM16 | QASYMM8_SIGNED
|
|
CLQLSTMLayer
|
|
src0 | src1 - src6 | src7 -src9 | src10 | src11 | dst0 | dst1 - dst2
|
---|
QASYMM8_SIGNED | QASYMM8 | S32 | QSYMM16 | QASYMM8_SIGNED | QSYMM16 | QASYMM8_SIGNED
|
|
QuantizationLayer
| Function to perform quantization layer
|
| NEQuantizationLayer
|
|
src | dst
|
---|
QASYMM8 | QASYMM8, QASYMM8_SIGNED, QASYMM16
| QASYMM8_SIGNED | QASYMM8, QASYMM8_SIGNED, QASYMM16
| F16 | QASYMM8, QASYMM8_SIGNED, QASYMM16
| F32 | QASYMM8, QASYMM8_SIGNED, QASYMM16
|
|
CLQuantizationLayer
|
|
src | dst
|
---|
QASYMM8 | QASYMM8, QASYMM8_SIGNED, QASYMM16
| QASYMM8_SIGNED | QASYMM8, QASYMM8_SIGNED, QASYMM16
| F16 | QASYMM8, QASYMM8_SIGNED, QASYMM16
| F32 | QASYMM8, QASYMM8_SIGNED, QASYMM16
|
|
Range
| Function to generates a sequence of numbers starting from START and extends by increments of 'STEP' up to but not including 'END'.
|
| NERange
|
|
dst
|
---|
U8
| S8
| U16
| S16
| U32
| S32
| F16
| F32
|
|
CLRange
|
|
dst
|
---|
U8
| S8
| QASYMM8
| U16
| S16
| U32
| S32
| F16
| F32
|
|
ReduceMean
| Function to perform reduce mean operation.
|
| NEReduceMean
|
|
src | dst
|
---|
QASYMM8 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED
| F16 | F16
| F32 | F32
|
|
CLReduceMean
|
|
src | dst
|
---|
QASYMM8 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED
| F16 | F16
| F32 | F32
|
|
ReductionOperation
| Function to perform reduce with the following operations - ARG_IDX_MAX: Index of the max value - ARG_IDX_MIN: Index of the min value - MEAN_SUM: Mean of sum - PROD: Product - SUM_SQUARE: Sum of squares - SUM: Sum - MIN: Min - MAX: Max
|
- ANEURALNETWORKS_REDUCE_ALL
- ANEURALNETWORKS_REDUCE_ANY
- ANEURALNETWORKS_REDUCE_MAX
- ANEURALNETWORKS_REDUCE_MIN
- ANEURALNETWORKS_REDUCE_PROD
- ANEURALNETWORKS_REDUCE_SUM
| NEReductionOperation
|
|
src | dst
|
---|
QASYMM8 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED
| F16 | F16
| F32 | F32
| S32 | S32
|
|
CLReductionOperation
|
|
src | dst
|
---|
QASYMM8 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED
| F16 | F16
| F32 | F32
| S32 | S32
|
|
ReorderLayer
| Reorders a tensor to a different weights format.
|
| NEReorderLayer
|
|
|
ReorgLayer
| Performs a reorganization layer of input tensor to the output tensor.
|
| NEReorgLayer
|
|
|
CLReorgLayer
|
|
|
ReshapeLayer
| Function to reshape a tensor.
|
- ANEURALNETWORKS_RESHAPE
- ANEURALNETWORKS_SQUEEZE
| NEReshapeLayer
|
|
|
CLReshapeLayer
|
|
|
Reverse
| Function to reverse tensor according to axis.
|
| NEReverse
|
|
src0 | src1 | dst
|
---|
All | U32, S32 | All
|
|
CLReverse
|
|
src0 | src1 | dst
|
---|
All | U32, S32 | All
|
|
RNNLayer
| Function to perform recurrent neural network layer.
|
| NERNNLayer
|
|
src0 | src1 | src2 | src3 | dst0 | dst1
|
---|
F16 | F16 | F16 | F16 | F16 | F16
| F32 | F32 | F32 | F32 | F32 | F32
|
|
CLRNNLayer
|
|
src0 | src1 | src2 | src3 | dst0 | dst1
|
---|
F16 | F16 | F16 | F16 | F16 | F16
| F32 | F32 | F32 | F32 | F32 | F32
|
|
ROIAlignLayer
| Function to perform ROI alignment.
|
- ANEURALNETWORKS_ROI_ALIGN
| NEROIAlignLayer
|
|
src0 | src1 | dst
|
---|
F16 | F16 | F16
| F32 | F32 | F32
| QASYMM8 | QASYMM16 | QASYMM8
| QASYMM8_SIGNED | QASYMM16 | QASYMM8_SIGNED
|
|
CLROIAlignLayer
|
|
src0 | src1 | dst
|
---|
F16 | F16 | F16
| F32 | F32 | F32
| QASYMM8 | QASYMM16 | QASYMM8
| QASYMM8_SIGNED | QASYMM16 | QASYMM8_SIGNED
|
|
ROIPoolingLayer
| Function to perform ROI pooling.
|
- ANEURALNETWORKS_ROI_POOLING
| NEROIPoolingLayer
|
|
src0 | src1 | dst
|
---|
F32 | U16 | F32
| QASYMM8 | U16 | QASYMM8
|
|
CLROIPoolingLayer
|
|
src0 | src1 | dst
|
---|
F16 | U16 | F16
| F32 | U16 | F32
| QASYMM8 | U16 | QASYMM8
|
|
Scale
| Function to perform resize a tensor using to interpolate: - Bilinear - Nearest neighbor
|
- ANEURALNETWORKS_RESIZE_BILINEAR
- ANEURALNETWORKS_RESIZE_NEAREST_NEIGHBOR
| NEScale
|
|
src | dst
|
---|
QASYMM8 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED
| F16 | F16
| F32 | F32
| U8 | U8
| S8 | S8
| S16 | S16
|
|
CLScale
|
|
src | dst
|
---|
QASYMM8 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED
| F16 | F16
| F32 | F32
| U8 | U8
| S16 | S16
|
|
Select
| Function to select values from 2 tensors depending on an input tensor of booleans.
|
| NESelect
|
|
src0 | src1 | src2 | dst
|
---|
U8 | All | All | All
|
|
CLSelect
|
|
src0 | src1 | src2 | dst
|
---|
U8 | All | All | All
|
|
Slice
| Function to perform tensor slicing.
|
| NESlice
|
|
|
CLSlice
|
|
|
SoftmaxLayer
| Function to compute a SoftmaxLayer and a Log SoftmaxLayer.
|
- ANEURALNETWORKS_LOG_SOFTMAX
- ANEURALNETWORKS_SOFTMAX
| NESoftmaxLayerGeneric
|
|
src | dst
|
---|
QASYMM8 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED
| F16 | F16
| F32 | F32
|
|
CLSoftmaxLayerGeneric
|
|
src | dst
|
---|
QASYMM8 | QASYMM8
| QASYMM8_SIGNED | QASYMM8_SIGNED
| F16 | F16
| F32 | F32
|
|
SpaceToBatchLayer
| Function to divide a tensor spatially.
|
- ANEURALNETWORKS_SPACE_TO_BATCH_ND
| NESpaceToBatchLayer
|
|
src0 | src1 | src2 | dst
|
---|
All | S32 | S32 | All
|
|
CLSpaceToBatchLayer
|
|
src0 | src1 | src2 | dst
|
---|
All | S32 | S32 | All
|
|
SpaceToDepthLayer
| Function to rearrange blocks of spatial data into depth.
|
- ANEURALNETWORKS_SPACE_TO_DEPTH
| NESpaceToDepthLayer
|
|
|
CLSpaceToDepthLayer
|
|
|
Split
| Function to split a tensor along a given axis.
|
| NESplit
|
|
|
CLSplit
|
|
|
StackLayer
| Function to stack tensors along an axis.
|
| NEStackLayer
|
|
|
CLStackLayer
|
|
|
StridedSlice
| Function to extract a strided slice of a tensor.
|
- ANEURALNETWORKS_STRIDED_SLICE
| NEStridedSlice
|
|
|
CLStridedSlice
|
|
|
Tile
| Function to construct a tensor by tiling a given tensor.
|
| NETile
|
|
|
CLTile
|
|
|
Transpose
| Function to transpose a 2D tensor.
|
- ANEURALNETWORKS_TRANSPOSE
| NETranspose
|
|
|
CLTranspose
|
|
|
Unstack
| Function to unpack a rank-R tensor into rank-(R-1) tensors.
|
| NEUnstack
|
|
|
CLUnstack
|
|
|
WinogradConvolutionLayer
| Function to do Winograd Convolution.
|
| NEWinogradConvolutionLayer
|
|
src0 | src1 | src2 | dst
|
---|
F16 | F16 | F16 | F16
| F32 | F32 | F32 | F32
|
|
CLWinogradConvolutionLayer
|
|
src0 | src1 | src2 | dst
|
---|
F16 | F16 | F16 | F16
| F32 | F32 | F32 | F32
|
|
*/
} // namespace