From 1a9c9f6a0a89a4356d33a59152f279bcab209991 Mon Sep 17 00:00:00 2001 From: Sadik Armagan Date: Thu, 5 Aug 2021 09:25:15 +0100 Subject: IVGCVSW-6051 'Arm NN Operator Coverage Page' * Created Arm NN Operator list page. Signed-off-by: Sadik Armagan Change-Id: I50dbdb78ea9714b0551e023f6ea7f017ad4b47bb --- docs/05_operator_list.dox | 3269 +++++++++++++++++++++++++++++++++++++++++++++ docs/Doxyfile | 1 + 2 files changed, 3270 insertions(+) create mode 100644 docs/05_operator_list.dox diff --git a/docs/05_operator_list.dox b/docs/05_operator_list.dox new file mode 100644 index 0000000000..4c4f6d10ed --- /dev/null +++ b/docs/05_operator_list.dox @@ -0,0 +1,3269 @@ +/// Copyright (c) 2021 ARM Limited and Contributors. All rights reserved. +/// +/// SPDX-License-Identifier: MIT +/// + +namespace armnn +{ +/** +@page operator_list Arm NN Operators + +@tableofcontents + +@section S5_1_operator_list Arm NN Operators + +Arm NN supports operators that are listed in below table. + +Arm NN supports a wide list of data-types. +The main data-types that the Machine Learning functions support are the following: + + +Arm NN supports the following data layouts (fast changing dimension from right to left): + +where N = batches, C = channels, H = height, W = width + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
Operator + Description + Equivalent Android NNAPI Operator + Backends + Data Layouts + Data Types +
AbsLayer + Layer to perform absolute operation. + +
    +
  • ANEURALNETWORKS_ABS +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
QASYMMS8 +
QASYMMU8 +
QSYMMS16 +
SIGNED32 +
+
CpuAcc + +
    +
  • All +
+ 		+ +
+
FLOAT16 +
FLOAT32 +
SIGNED32 +
+
GpuAcc + +
    +
  • All +
+ 		+ +
+
FLOAT16 +
FLOAT32 +
+
ActivationLayer + Layer to simulate an activation layer with the specified activation function. + +
    +
  • ANEURALNETWORKS_ABS +
  • ANEURALNETWORKS_ELU +
  • ANEURALNETWORKS_HARD_SWISH +
  • ANEURALNETWORKS_LOGISTIC +
  • ANEURALNETWORKS_PRELU +
  • ANEURALNETWORKS_RELU +
  • ANEURALNETWORKS_RELU1 +
  • ANEURALNETWORKS_RELU6 +
  • ANEURALNETWORKS_SQRT +
  • ANEURALNETWORKS_TANH +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
QASYMMS8 +
QASYMMU8 +
QSYMMS16 +
+
CpuAcc + +
    +
  • All +
+ 		+ +
+
QASYMMU8 +
QASYMMS8 +
QSYMMS16 +
FLOAT16 +
FLOAT32 +
+
GpuAcc + +
    +
  • All +
+ 		+ +
+
QASYMMU8 +
QASYMMS8 +
QSYMMS16 +
FLOAT16 +
FLOAT32 +
+
AdditionLayer + Layer to add 2 tensors. + +
    +
  • ANEURALNETWORKS_ADD +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
QASYMMS8 +
QASYMMU8 +
QSYMMS16 +
SIGNED32 +
+
CpuAcc + +
    +
  • All +
+ 		+ +
+
QASYMMU8 +
QASYMMS8 +
QSYMMS16 +
SIGNED32 +
FLOAT16 +
FLOAT32 +
+
GpuAcc + +
    +
  • All +
+ 		+ +
+
QASYMMU8 +
QASYMMS8 +
QSYMMS16 +
SIGNED32 +
FLOAT16 +
FLOAT32 +
+
ArgMinMaxLayer + Layer to calculate the index of the minimum or maximum values in a tensor + based on an axis. + +
    +
  • ANEURALNETWORKS_ARGMAX +
  • ANEURALNETWORKS_ARGMIN +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
QASYMMS8 +
QASYMMU8 +
QSYMMS16 +
SIGNED32 +
SIGNED64 +
+
CpuAcc + +
    +
  • All +
+ 		+ +
+
QASYMMU8 +
QASYMMS8 +
SIGNED32 +
FLOAT16 +
FLOAT32 +
+
GpuAcc + +
    +
  • All +
+ 		+ +
+
QASYMMU8 +
QASYMMS8 +
SIGNED32 +
FLOAT16 +
FLOAT32 +
+
BatchNormalizationLayer + Layer to perform batch normalization. + +
    +
  • N/A +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
QASYMMS8 +
QASYMMU8 +
QSYMMS16 +
+
CpuAcc + +
    +
  • NHWC +
  • NCHW +
+ 		+ +
+
FLOAT32 +
FLOAT16 +
+
GpuAcc + +
    +
  • NHWC +
  • NCHW +
+ 		+ +
+
FLOAT32 +
FLOAT16 +
+
BatchToSpaceNdLayer + Layer to perform a batch to space transformation. + +
    +
  • ANEURALNETWORKS_BATCH_TO_SPACE_ND +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
QASYMMS8 +
QASYMMU8 +
QSYMMS16 +
+
CpuAcc + +
    +
  • NHWC +
  • NCHW +
+ 		+ +
+
All +
+
GpuAcc + +
    +
  • NHWC +
  • NCHW +
+ 		+ +
+
All +
+
CastLayer + Layer to cast a tensor to a type. + +
    +
  • ANEURALNETWORKS_CAST +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
QSYMMS8 +
QASYMMS8 +
QASYMMU8 +
QSYMMS16 +
SIGNED32 +
+
CpuAcc + +
    +
  • All +
+ 		+ +
+
QASYMMS8 +
QASYMMU8 +
FLOAT16 +
SIGNED32 +
FLOAT32 +
+
GpuAcc + +
    +
  • All +
+ 		+ +
+
QASYMMS8 +
QASYMMU8 +
SIGNED32 +
FLOAT16 +
FLOAT32 +
+
ComparisonLayer + Layer to compare 2 tensors. + +
    +
  • ANEURALNETWORKS_EQUAL +
  • ANEURALNETWORKS_GREATER +
  • ANEURALNETWORKS_GREATER_EQUAL +
  • ANEURALNETWORKS_LESS +
  • ANEURALNETWORKS_LESS_EQUAL +
  • ANEURALNETWORKS_NOT_EQUAL +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
BOOLEAN +
QASYMMS8 +
QASYMMU8 +
QSYMMS16 +
SIGNED32 +
+
CpuAcc + +
    +
  • All +
+ 		+ +
+
All +
+
GpuAcc + +
    +
  • All +
+ 		+ +
+
All +
+
ConcatLayer + Layer to concatenate tensors along a given axis. + +
    +
  • ANEURALNETWORKS_CONCATENATION +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
QASYMMS8 +
QASYMMU8 +
QSYMMS16 +
+
CpuAcc + +
    +
  • All +
+ 		+ +
+
QASYMMU8 +
QASYMMS8 +
FLOAT16 +
FLOAT32 +
+
GpuAcc + +
    +
  • All +
+ 		+ +
+
QASYMMU8 +
QASYMMS8 +
FLOAT16 +
FLOAT32 +
+
ConstantLayer + Layer to provide a constant tensor. + +
    +
  • N/A +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
QASYMMS8 +
QASYMMU8 +
QSYMMS8 +
QSYMMS16 +
SIGNED32 +
+
CpuAcc + +
    +
  • All +
+ 		+ +
+
All +
+
GpuAcc + +
    +
  • All +
+ 		+ +
+
All +
+
ConvertBf16ToFp32Layer + Layer to convert BFloat16 tensor to Float32 tensor. + +
    +
  • N/A +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT32 +
+
CpuAcc + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT32 +
+
GpuAcc + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT32 +
+
ConvertFp16ToFp32Layer + Layer to convert Float16 tensor to Float32 tensor. + +
    +
  • N/A +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
FLOAT16 +
FLOAT32 +
+
CpuAcc + +
    +
  • All +
+ 		+ +
+
FLOAT16 +
FLOAT32 +
+
GpuAcc + +
    +
  • All +
+ 		+ +
+
FLOAT16 +
FLOAT32 +
+
ConvertFp32ToBf16Layer + Layer to convert Float32 tensor to BFloat16 tensor. + +
    +
  • N/A +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT32 +
+
CpuAcc + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT32 +
+
GpuAcc + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT32 +
+
ConvertFp32ToFp16Layer + Layer to convert Float32 tensor to Float16 tensor. + +
    +
  • N/A +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
FLOAT16 +
FLOAT32 +
+
CpuAcc + +
    +
  • All +
+ 		+ +
+
FLOAT16 +
FLOAT32 +
+
GpuAcc + +
    +
  • All +
+ 		+ +
+
FLOAT16 +
FLOAT32 +
+
Convolution2dLayer + Layer to compute a convolution operation. + +
    +
  • ANEURALNETWORKS_CONV_2D +
  • ANEURALNETWORKS_GROUPED_CONV_2D +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
QASYMMS8 +
QASYMMU8 +
QSYMMS16 +
+
CpuAcc + +
    +
  • NHWC +
  • NCHW +
+ 		+ +
+
SIGNED32 +
FLOAT16 +
FLOAT32 +
QASYMMU8 +
QASYMMS8 +
QUANTIZEDSYMM8PERAXIS +
+
GpuAcc + +
    +
  • NHWC +
  • NCHW +
+ 		+ +
+
SIGNED32 +
FLOAT16 +
FLOAT32 +
QASYMMU8 +
QASYMMS8 +
QUANTIZEDSYMM8PERAXIS +
+
DebugLayer + Layer to print out inter layer tensor information. + +
    +
  • N/A +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
QASYMMS8 +
QASYMMU8 +
QSYMMS8 +
QSYMMS16 +
SIGNED32 +
+
DepthToSpaceLayer + Layer to perform Depth to Space transformation. + +
    +
  • ANEURALNETWORKS_DEPTH_TO_SPACE +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
QASYMMS8 +
QASYMMU8 +
QSYMMS16 +
+
CpuAcc + +
    +
  • NHWC +
  • NCHW +
+ 		+ +
+
All +
+
GpuAcc + +
    +
  • NHWC +
  • NCHW +
+ 		+ +
+
All +
+
DepthwiseConvolution2dLayer + Layer to compute a deconvolution or transpose convolution. + +
    +
  • ANEURALNETWORKS_DEPTHWISE_CONV_2D +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
QASYMMS8 +
QASYMMU8 +
QSYMMS8 +
QSYMMS16 +
+
CpuAcc + +
    +
  • NHWC +
  • NCHW +
+ 		+ +
+
FLOAT16 +
FLOAT32 +
SIGNED32 +
QASYMMU8 +
QASYMMS8 +
QUANTIZEDSYMM8PERAXIS +
+
GpuAcc + +
    +
  • NHWC +
  • NCHW +
+ 		+ +
+
FLOAT16 +
FLOAT32 +
SIGNED32 +
QASYMMU8 +
QASYMMS8 +
QUANTIZEDSYMM8PERAXIS +
+
DequantizeLayer + Layer to dequantize the values in a tensor. + +
    +
  • ANEURALNETWORKS_DEQUANTIZE +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
QASYMMS8 +
QASYMMU8 +
QSYMMS8 +
QSYMMS16 +
+
CpuAcc + +
    +
  • All +
+ 		+ +
+
FLOAT16 +
FLOAT32 +
QASYMMU8 +
QASYMMS8 +
QUANTIZEDSYMM8PERAXIS +
QSYMMS8 +
QSYMMS16 +
+
GpuAcc + +
    +
  • All +
+ 		+ +
+
FLOAT16 +
FLOAT32 +
QASYMMU8 +
QASYMMS8 +
QUANTIZEDSYMM8PERAXIS +
QSYMMS8 +
QSYMMS16 +
+
DetectionPostProcessLayer + Layer to generate the detection output based on center size encoded boxes, class prediction and anchors by doing non maximum suppression (NMS). + +
    +
  • ANEURALNETWORKS_DETECTION_POSTPROCESSING +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
QASYMMS8 +
QASYMMU8 +
QSYMMS16 +
+
CpuAcc + +
    +
  • All +
+ 		+ +
+
QASYMMU8 +
QASYMMS8 +
FLOAT32 +
+
DivisionLayer + Layer to divide 2 tensors. + +
    +
  • ANEURALNETWORKS_DIV +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
QASYMMS8 +
QASYMMU8 +
QSYMMS16 +
SIGNED32 +
+
CpuAcc + +
    +
  • All +
+ 		+ +
+
FLOAT16 +
FLOAT32 +
+
GpuAcc + +
    +
  • All +
+ 		+ +
+
FLOAT16 +
FLOAT32 +
+
ElementwiseBaseLayer + Layer to perform Add - Div - Max - Min - Mul operations. + +
    +
  • ANEURALNETWORKS_ADD +
  • ANEURALNETWORKS_DIV +
  • ANEURALNETWORKS_MAXIMUM +
  • ANEURALNETWORKS_MINIMUM +
  • ANEURALNETWORKS_MUL +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
QASYMMS8 +
QASYMMU8 +
QSYMMS16 +
SIGNED32 +
+
CpuAcc + +
    +
  • All +
+ 		+ +
+
QASYMMU8 +
QASYMMS8 +
QSYMMS16 +
SIGNED32 +
FLOAT16 +
FLOAT32 +
+
GpuAcc + +
    +
  • All +
+ 		+ +
+
QASYMMU8 +
QASYMMS8 +
QSYMMS16 +
SIGNED32 +
FLOAT16 +
FLOAT32 +
+
ElementwiseUnaryLayer + Layer to perform Rsqrt - Exp - Neg - Log - Abs - Sin - Sqrt operations. + +
    +
  • ANEURALNETWORKS_ABS +
  • ANEURALNETWORKS_EXP +
  • ANEURALNETWORKS_LOG +
  • ANEURALNETWORKS_NEG +
  • ANEURALNETWORKS_RSQRT +
  • ANEURALNETWORKS_SIN +
  • ANEURALNETWORKS_SQRT +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
QASYMMS8 +
QASYMMU8 +
QSYMMS16 +
+
CpuAcc + +
    +
  • All +
+ 		+ +
+
FLOAT16 +
FLOAT32 +
SIGNED32 +
+
GpuAcc + +
    +
  • All +
+ 		+ +
+
FLOAT16 +
FLOAT32 +
+
FakeQuantizationLayer + Layer to quantize float values and dequantize afterwards. The current implementation does not dequantize the values. + +
    +
  • N/A +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
FLOAT32 +
+
FillLayer + Layer to set the values of a tensor with a given value. + +
    +
  • ANEURALNETWORKS_FILL +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
FLOAT16 +
FLOAT32 +
SIGNED32 +
+
CpuAcc + +
    +
  • All +
+ 		+ +
+
All +
+
GpuAcc + +
    +
  • All +
+ 		+ +
+
All +
+
FloorLayer + Layer to round the value to the lowest whole number. + +
    +
  • ANEURALNETWORKS_FLOOR +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
+
CpuAcc + +
    +
  • All +
+ 		+ +
+
FLOAT32 +
FLOAT16 +
+
GpuAcc + +
    +
  • All +
+ 		+ +
+
FLOAT32 +
FLOAT16 +
+
FullyConnectedLayer + Layer to perform a fully connected / dense operation. + +
    +
  • ANEURALNETWORKS_FULLY_CONNECTED +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
QASYMMS8 +
QASYMMU8 +
QSYMMS16 +
+
CpuAcc + +
    +
  • NHWC +
  • NCHW +
+ 		+ +
+
SIGNED32 +
FLOAT16 +
FLOAT32 +
QASYMMU8 +
QASYMMS8 +
+
GpuAcc + +
    +
  • NHWC +
  • NCHW +
+ 		+ +
+
SIGNED32 +
FLOAT16 +
FLOAT32 +
QASYMMU8 +
QASYMMS8 +
+
GatherLayer + Layer to perform the gather operation along the chosen axis. + +
    +
  • ANEURALNETWORKS_GATHER +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
QASYMMS8 +
QASYMMU8 +
QSYMMS16 +
SIGNED32 +
+
CpuAcc + +
    +
  • All +
+ 		+ +
+
All +
+
GpuAcc + +
    +
  • All +
+ 		+ +
+
All +
+
InputLayer + Special layer used to provide input data to the computational network. + +
    +
  • N/A +
+ 		All + +
    +
  • All +
+ 		+ +
+
All +
+
InstanceNormalizationLayer + Layer to perform an instance normalization on a given axis. + +
    +
  • ANEURALNETWORKS_INSTANCE_NORMALIZATION +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
+
CpuAcc + +
    +
  • NHWC +
  • NCHW +
+ 		+ +
+
FLOAT16 +
FLOAT32 +
+
GpuAcc + +
    +
  • NHWC +
  • NCHW +
+ 		+ +
+
FLOAT16 +
FLOAT32 +
+
L2NormalizationLayer + Layer to perform an L2 normalization on a given axis. + +
    +
  • ANEURALNETWORKS_L2_NORMALIZATION +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
QASYMMS8 +
QASYMMU8 +
QSYMMS16 +
+
CpuAcc + +
    +
  • NHWC +
  • NCHW +
+ 		+ +
+
FLOAT16 +
FLOAT32 +
+
GpuAcc + +
    +
  • NHWC +
  • NCHW +
+ 		+ +
+
FLOAT16 +
FLOAT32 +
+
LogSoftmaxLayer + Layer to perform the log softmax activations given logits. + +
    +
  • N/A +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
+
CpuAcc + +
    +
  • All +
+ 		+ +
+
QASYMMU8 +
QASYMMS8 +
FLOAT16 +
FLOAT32 +
+
GpuAcc + +
    +
  • All +
+ 		+ +
+
QASYMMU8 +
QASYMMS8 +
FLOAT16 +
FLOAT32 +
+
LogicalBinaryLayer + Layer to perform Logical AND - Logical NOT - Logical OR operations. + +
    +
  • ANEURALNETWORKS_LOGICAL_AND +
  • ANEURALNETWORKS_LOGICAL_NOT +
  • ANEURALNETWORKS_LOGICAL_OR +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BOOLEAN +
+
CpuAcc + +
    +
  • All +
+ 		+ +
+
BOOLEAN +
+
GpuAcc + +
    +
  • All +
+ 		+ +
+
BOOLEAN +
+
LstmLayer + Layer to perform a single time step in a Long Short-Term Memory (LSTM) operation. + +
    +
  • ANEURALNETWORKS_LSTM +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
QSYMMS16 +
+
CpuAcc + +
    +
  • All +
+ 		+ +
+
FLOAT16 +
FLOAT32 +
+
GpuAcc + +
    +
  • All +
+ 		+ +
+
FLOAT16 +
FLOAT32 +
+
MapLayer + Layer to perform map operation on tensor. + +
    +
  • N/A +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
All +
+
CpuAcc + +
    +
  • All +
+ 		+ +
+
All +
+
GpuAcc + +
    +
  • All +
+ 		+ +
+
All +
+
MaximumLayer + Layer to perform an elementwise maximum of two tensors. + +
    +
  • N/A +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
QASYMMS8 +
QASYMMU8 +
QSYMMS16 +
SIGNED32 +
+
CpuAcc + +
    +
  • All +
+ 		+ +
+
QASYMMU8 +
QASYMMS8 +
FLOAT16 +
FLOAT32 +
SIGNED32 +
+
GpuAcc + +
    +
  • All +
+ 		+ +
+
QASYMMU8 +
QASYMMS8 +
QSYMMS16 +
FLOAT16 +
FLOAT32 +
SIGNED32 +
+
MeanLayer + Layer to perform reduce mean operation. + +
    +
  • ANEURALNETWORKS_MEAN +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
QASYMMS8 +
QASYMMU8 +
QSYMMS16 +
+
CpuAcc + +
    +
  • All +
+ 		+ +
+
QASYMMU8 +
QASYMMS8 +
FLOAT16 +
FLOAT32 +
+
GpuAcc + +
    +
  • All +
+ 		+ +
+
QASYMMU8 +
QASYMMS8 +
FLOAT16 +
FLOAT32 +
+
MemCopyLayer + Layer to perform memory copy operation. + +
    +
  • N/A +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
QASYMMS8 +
QASYMMU8 +
QSYMMS16 +
BOOLEAN +
+
CpuAcc + +
    +
  • All +
+ 		+ +
+
All +
+
GpuAcc + +
    +
  • All +
+ 		+ +
+
All +
+
MemImportLayer + Layer to perform memory import operation. + +
    +
  • N/A +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
All +
+
CpuAcc + +
    +
  • All +
+ 		+ +
+
All +
+
GpuAcc + +
    +
  • All +
+ 		+ +
+
All +
+
MergeLayer + Layer to concatenate tensors along a given axis. + +
    +
  • ANEURALNETWORKS_CONCATENATION +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
QASYMMS8 +
QASYMMU8 +
QSYMMS16 +
+
CpuAcc + +
    +
  • All +
+ 		+ +
+
QASYMMU8 +
QASYMMS8 +
FLOAT16 +
FLOAT32 +
+
GpuAcc + +
    +
  • All +
+ 		+ +
+
QASYMMU8 +
QASYMMS8 +
FLOAT16 +
FLOAT32 +
+
MinimumLayer + Layer to perform an elementwise minimum of two tensors. + +
    +
  • ANEURALNETWORKS_MINIMUM +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
QASYMMS8 +
QASYMMU8 +
QSYMMS16 +
SIGNED32 +
+
CpuAcc + +
    +
  • All +
+ 		+ +
+
QASYMMU8 +
QASYMMS8 +
QSYMMS16 +
FLOAT16 +
FLOAT32 +
+
GpuAcc + +
    +
  • All +
+ 		+ +
+
QASYMMU8 +
QASYMMS8 +
QSYMMS16 +
FLOAT16 +
FLOAT32 +
SIGNED32 +
+
MultiplicationLayer + Layer to perform an elementwise multiplication of two tensors. + +
    +
  • ANEURALNETWORKS_MUL +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
QASYMMS8 +
QASYMMU8 +
QSYMMS16 +
SIGNED32 +
+
CpuAcc + +
    +
  • All +
+ 		+ +
+
QASYMMU8 +
QASYMMS8 +
QSYMMS16 +
SIGNED32 +
FLOAT16 +
FLOAT32 +
+
GpuAcc + +
    +
  • All +
+ 		+ +
+
QASYMMU8 +
QASYMMS8 +
QSYMMS16 +
SIGNED32 +
FLOAT16 +
FLOAT32 +
SIGNED32 +
+
NormalizationLayer + Layer to compute normalization operation. + +
    +
  • ANEURALNETWORKS_LOCAL_RESPONSE_NORMALIZATION +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
QASYMMS8 +
QASYMMU8 +
QSYMMS16 +
+
CpuAcc + +
    +
  • NHWC +
  • NCHW +
+ 		+ +
+
FLOAT32 +
FLOAT16 +
+
GpuAcc + +
    +
  • NHWC +
  • NCHW +
+ 		+ +
+
FLOAT32 +
FLOAT16 +
+
OutputLayer + A special layer providing access to a user supplied buffer into which the output of a network can be written. + +
    +
  • N/A +
+ 		All + +
    +
  • All +
+ 		+ +
+
All +
+
PadLayer + Layer to pad a tensor. + +
    +
  • ANEURALNETWORKS_PAD +
  • ANEURALNETWORKS_PAD_V2 +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
QASYMMS8 +
QASYMMU8 +
QSYMMS16 +
+
CpuAcc + +
    +
  • NHWC +
  • NCHW +
+ 		+ +
+
All +
+
GpuAcc + +
    +
  • NHWC +
  • NCHW +
+ 		+ +
+
All +
+
PermuteLayer + Layer to transpose an ND tensor. + +
    +
  • ANEURALNETWORKS_TRANSPOSE +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
QASYMMS8 +
QASYMMU8 +
QSYMMS16 +
+
CpuAcc + +
    +
  • NHWC +
  • NCHW +
+ 		+ +
+
All +
+
GpuAcc + +
    +
  • NHWC +
  • NCHW +
+ 		+ +
+
All +
+
Pooling2dLayer + Layer to perform pooling with the specified pooling operation. + +
    +
  • ANEURALNETWORKS_AVERAGE_POOL_2D +
  • ANEURALNETWORKS_L2_POOL_2D +
  • ANEURALNETWORKS_MAX_POOL_2D +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
QASYMMS8 +
QASYMMU8 +
QSYMMS16 +
+
CpuAcc + +
    +
  • NHWC +
  • NCHW +
+ 		+ +
+
QASYMMU8 +
QASYMMS8 +
FLOAT16 +
FLOAT32 +
+
GpuAcc + +
    +
  • NHWC +
  • NCHW +
+ 		+ +
+
QASYMMU8 +
QASYMMS8 +
FLOAT16 +
FLOAT32 +
+
PreCompiledLayer + Opaque layer provided by a backend which provides an executable representation of a subgraph from the original network. + +
    +
  • N/A +
+ 		N/A + N/A + N/A +
PreluLayer + Layer to compute the activation layer with the PRELU activation function. + +
    +
  • ANEURALNETWORKS_PRELU +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
QASYMMS8 +
QASYMMU8 +
QSYMMS16 +
+
CpuAcc + +
    +
  • All +
+ 		+ +
+
QASYMMU8 +
QASYMMS8 +
FLOAT16 +
FLOAT32 +
+
GpuAcc + +
    +
  • All +
+ 		+ +
+
QASYMMU8 +
QASYMMS8 +
FLOAT16 +
FLOAT32 +
+
QLstmLayer + Layer to perform quantized LSTM (Long Short-Term Memory) operation. + +
    +
  • ANEURALNETWORKS_QUANTIZED_LSTM +
  • ANEURALNETWORKS_QUANTIZED_16BIT_LSTM +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
All +
+
CpuAcc + +
    +
  • All +
+ 		+ +
+
QASYMMS8 +
QASYMMU8 +
SIGNED32 +
QSYMMS16 +
+
GpuAcc + +
    +
  • All +
+ 		+ +
+
QASYMMS8 +
QASYMMU8 +
SIGNED32 +
QSYMMS16 +
+
QuantizeLayer + Layer to perform quantization operation. + +
    +
  • ANEURALNETWORKS_QUANTIZE +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
QASYMMS8 +
QASYMMU8 +
QSYMMS8 +
QSYMMS16 +
+
CpuAcc + +
    +
  • All +
+ 		+ +
+
QASYMMU8 +
QASYMMS8 +
QASYMM16 +
FLOAT16 +
FLOAT32 +
+
GpuAcc + +
    +
  • All +
+ 		+ +
+
QASYMMU8 +
QASYMMS8 +
QASYMM16 +
FLOAT16 +
FLOAT32 +
+
QuantizedLstmLayer + Layer to perform quantized LSTM (Long Short-Term Memory) operation. + +
    +
  • ANEURALNETWORKS_QUANTIZED_LSTM +
  • ANEURALNETWORKS_QUANTIZED_16BIT_LSTM +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
All +
+
CpuAcc + +
    +
  • All +
+ 		+ +
+
SIGNED32 +
QASYMMU8 +
QSYMMS16 +
+
GpuAcc + +
    +
  • All +
+ 		+ +
+
SIGNED32 +
QASYMMU8 +
QSYMMS16 +
+
RankLayer + Layer to perform a rank operation. + +
    +
  • ANEURALNETWORKS_RANK +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
All +
+
CpuAcc + +
    +
  • All +
+ 		+ +
+
All +
+
GpuAcc + +
    +
  • All +
+ 		+ +
+
All +
+
ReduceLayer + Layer 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_MAX +
  • ANEURALNETWORKS_REDUCE_MIN +
  • ANEURALNETWORKS_REDUCE_SUM +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
QASYMMS8 +
QASYMMU8 +
QSYMMS16 +
SIGNED32 +
+
CpuAcc + +
    +
  • All +
+ 		+ +
+
QASYMMU8 +
QASYMMS8 +
FLOAT16 +
FLOAT32 +
SIGNED32 +
+
GpuAcc + +
    +
  • All +
+ 		+ +
+
QASYMMU8 +
QASYMMS8 +
FLOAT16 +
FLOAT32 +
SIGNED32 +
+
ReshapeLayer + Layer to reshape a tensor. + +
    +
  • ANEURALNETWORKS_RESHAPE +
  • ANEURALNETWORKS_SQUEEZE +
  • ANEURALNETWORKS_EXPAND_DIMS +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
QASYMMS8 +
QASYMMU8 +
QSYMMS16 +
SIGNED32 +
BOOLEAN +
+
CpuAcc + +
    +
  • All +
+ 		+ +
+
All +
+
GpuAcc + +
    +
  • All +
+ 		+ +
+
All +
+
ResizeLayer + Layer to perform resize of a tensor using one of the interpolation methods: - Bilinear - Nearest Neighbor. + +
    +
  • ANEURALNETWORKS_RESIZE_BILINEAR +
  • ANEURALNETWORKS_RESIZE_NEAREST_NEIGHBOR +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
QASYMMS8 +
QASYMMU8 +
QSYMMS16 +
+
CpuAcc + +
    +
  • NHWC +
  • NCHW +
+ 		+ +
+
QASYMMU8 +
QASYMMS8 +
FLOAT16 +
FLOAT32 +
+
GpuAcc + +
    +
  • NHWC +
  • NCHW +
+ 		+ +
+
QASYMMU8 +
QASYMMS8 +
FLOAT16 +
FLOAT32 +
+
RsqrtLayer + Layer to perform Rsqrt operation. + +
    +
  • ANEURALNETWORKS_RSQRT +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
QASYMMS8 +
QASYMMU8 +
QSYMMS16 +
SIGNED32 +
+
CpuAcc + +
    +
  • All +
+ 		+ +
+
FLOAT16 +
FLOAT32 +
SIGNED32 +
+
GpuAcc + +
    +
  • All +
+ 		+ +
+
FLOAT16 +
FLOAT32 +
+
ShapeLayer + Layer to return the shape of the input tensor. + +
    +
  • N/A +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
All +
+
CpuAcc + +
    +
  • All +
+ 		+ +
+
All +
+
GpuAcc + +
    +
  • All +
+ 		+ +
+
All +
+
SliceLayer + Layer to perform tensor slicing. + +
    +
  • ANEURALNETWORKS_SLICE +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT32 +
QASYMMS8 +
QASYMMU8 +
QSYMMS16 +
+
CpuAcc + +
    +
  • All +
+ 		+ +
+
All +
+
GpuAcc + +
    +
  • All +
+ 		+ +
+
All +
+
SoftmaxLayer + Layer to perform softmax, log-softmax operation over the specified axis. + +
    +
  • ANEURALNETWORKS_LOG_SOFTMAX +
  • ANEURALNETWORKS_SOFTMAX +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
QASYMMS8 +
QASYMMU8 +
QSYMMS8 +
QSYMMS16 +
+
CpuAcc + +
    +
  • All +
+ 		+ +
+
QASYMMU8 +
QASYMMS8 +
FLOAT16 +
FLOAT32 +
+
GpuAcc + +
    +
  • All +
+ 		+ +
+
QASYMMU8 +
QASYMMS8 +
FLOAT16 +
FLOAT32 +
+
SpaceToBatchNdLayer + Layer to divide spatial dimensions of the tensor into a grid of blocks and interleaves these blocks with the batch dimension. + +
    +
  • ANEURALNETWORKS_SPACE_TO_BATCH_ND +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
QASYMMS8 +
QASYMMU8 +
QSYMMS16 +
+
CpuAcc + +
    +
  • NHWC +
  • NCHW +
+ 		+ +
+
All +
+
GpuAcc + +
    +
  • NHWC +
  • NCHW +
+ 		+ +
+
All +
+
SpaceToDepthLayer + Layer to rearrange blocks of spatial data into depth. + +
    +
  • ANEURALNETWORKS_SPACE_TO_DEPTH +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
QASYMMS8 +
QASYMMU8 +
QSYMMS16 +
+
CpuAcc + +
    +
  • NHWC +
  • NCHW +
+ 		+ +
+
All +
+
GpuAcc + +
    +
  • NHWC +
  • NCHW +
+ 		+ +
+
All +
+
SplitterLayer + Layer to split a tensor along a given axis. + +
    +
  • ANEURALNETWORKS_SPLIT +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
QASYMMS8 +
QASYMMU8 +
QSYMMS16 +
+
CpuAcc + +
    +
  • All +
+ 		+ +
+
All +
+
GpuAcc + +
    +
  • All +
+ 		+ +
+
All +
+
StackLayer + Layer to stack tensors along an axis. + +
    +
  • N/A +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
QASYMMS8 +
QASYMMU8 +
QSYMMS16 +
+
CpuAcc + +
    +
  • All +
+ 		+ +
+
All +
+
GpuAcc + +
    +
  • All +
+ 		+ +
+
All +
+
StandInLayer + A layer to represent "unknown" or "unsupported" operations in the input graph. It has a configurable number of input and output slots and an optional name. + +
    +
  • N/A +
+ 		N/A + N/A + N/A +
StridedSliceLayer + Layer to extract a strided slice of a tensor. + +
    +
  • ANEURALNETWORKS_STRIDED_SLICE +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT32 +
QASYMMS8 +
QASYMMU8 +
QSYMMS16 +
+
CpuAcc + +
    +
  • All +
+ 		+ +
+
All +
+
GpuAcc + +
    +
  • All +
+ 		+ +
+
All +
+
SubtractionLayer + Layer to perform an elementwise subtract of 2 tensors. + +
    +
  • ANEURALNETWORKS_SUB +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
QASYMMS8 +
QASYMMU8 +
QSYMMS16 +
SIGNED32 +
+
CpuAcc + +
    +
  • All +
+ 		+ +
+
QASYMMU8 +
QASYMMS8 +
QSYMMS16 +
SIGNED32 +
FLOAT16 +
FLOAT32 +
+
GpuAcc + +
    +
  • All +
+ 		+ +
+
QASYMMU8 +
QASYMMS8 +
QSYMMS16 +
SIGNED32 +
FLOAT16 +
FLOAT32 +
+
TransposeConvolution2dLayer + Layer to perform 2D transpose convolution (deconvolution) operation. + +
    +
  • ANEURALNETWORKS_TRANSPOSE_CONV_2D +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
QASYMMS8 +
QASYMMU8 +
QSYMMS8 +
QSYMMS16 +
+
CpuAcc + +
    +
  • NHWC +
  • NCHW +
+ 		+ +
+
SIGNED32 +
FLOAT16 +
FLOAT32 +
QASYMMU8 +
QASYMMS8 +
QUANTIZEDSYMM8PERAXIS +
+
GpuAcc + +
    +
  • NHWC +
  • NCHW +
+ 		+ +
+
SIGNED32 +
FLOAT16 +
FLOAT32 +
QASYMMU8 +
QASYMMS8 +
QUANTIZEDSYMM8PERAXIS +
+
TransposeLayer + Layer to transpose a tensor. + +
    +
  • ANEURALNETWORKS_TRANSPOSE +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
BFLOAT16 +
FLOAT16 +
FLOAT32 +
QASYMMS8 +
QASYMMU8 +
QSYMMS16 +
+
CpuAcc + +
    +
  • All +
+ 		+ +
+
All +
+
GpuAcc + +
    +
  • All +
+ 		+ +
+
All +
+
UnidirectionalSquenceLstmLayer + Layer to perform unidirectional LSTM operation. + +
    +
  • ANEURALNETWORKS_UNIDIRECTIONAL_SEQUENCE_LSTM +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
All +
+
CpuAcc + +
    +
  • NHWC +
  • NCHW +
+ 		+ +
+
SIGNED32 +
FLOAT16 +
FLOAT32 +
QASYMMU8 +
QASYMMS8 +
QUANTIZEDSYMM8PERAXIS +
+
GpuAcc + +
    +
  • NHWC +
  • NCHW +
+ 		+ +
+
SIGNED32 +
FLOAT16 +
FLOAT32 +
QASYMMU8 +
QASYMMS8 +
QUANTIZEDSYMM8PERAXIS +
+
UnmapLayer + Layer to perform unmap operation on tensor. + +
    +
  • N/A +
+ 		CpuRef + +
    +
  • All +
+ 		+ +
+
All +
+
CpuAcc + +
    +
  • NHWC +
  • NCHW +
+ 		+ +
+
All +
+
GpuAcc + +
    +
  • NHWC +
  • NCHW +
+ 		+ +
+
All +
+
+ +*/ +} // namespace \ No newline at end of file diff --git a/docs/Doxyfile b/docs/Doxyfile index fc28f214ff..6516f0fde5 100644 --- a/docs/Doxyfile +++ b/docs/Doxyfile @@ -820,6 +820,7 @@ INPUT = ./docs/01_00_software_tools.dox \ ./docs/02_build_guides.dox \ ./docs/03_use_guides.dox \ ./docs/04_contributor.dox \ + ./docs/05_operator_list.dox \ ./docs/FAQ.md \ ./tests/ImageCSVFileGenerator/README.md \ ./tests/ImageTensorGenerator/README.md \ -- cgit v1.2.1