Lite算子支持

查看源文件

本文列举MindSpore Lite支持的算子。

操作名
 

CPU
FP16

CPU
FP32

CPU
Int8

CPU
UInt8

GPU
FP16

GPU
FP32

NPU
 

TensorRT
 

Ascend
(Ascend310)

支持的TensorFlow Lite算子

支持的Caffe算子

支持的Onnx算子

支持的TensorFlow算子

Abs

Abs

Abs

Abs

Add

Add

Add, Int8Add

Add, AddV2

Adder

adder_f

AddGrad

AddN

AddN

Assert

Assert

Argmax

Argmax

ArgMax

ArgMax

ArgMax

Argmin

Argmin

ArgMin

AvgPool

MeanPooling

Pooling

AveragePool,
GlobalAveragePool,
Int8AveragePool

AvgPool

AvgPoolGrad

BatchNorm

BatchNorm

BatchNormalization

BatchNormGrad

BatchToSpace

BatchToSpace,
BatchToSpaceND

BatchToSpace,
BatchToSpaceND

BiasAdd

BiasAdd

BiasAdd

BiasAddGrad

BroadcastTo

BroadcastTo

Expand

BroadcastTo

Cast

Cast,
QUANTIZE,
DEQUANTIZE

Cast

Cast

Ceil

Ceil

Ceil

Ceil

Concat

Concat

Concat

Concat

ConcatV2

ConstantOfShape

ConstantOfShape

Conv2d

Conv2D

Convolution

Conv, Int8Conv,
ConvRelu,
Int8ConvRelu

Conv2D

Conv2DBackpropFilterFusion

Conv2DBackpropInputFusion

Conv2dGrad

Conv2dTranspose

DeConv2D

Deconvolution

ConvTranspose

Conv2DBackpropInput

Conv2dTransposeGrad

Cos

Cos

Cos

Cos

Crop

Crop

CropAndResize

CropAndResize

CumSum

Cumsum

CustomExtractFeatures

ExtractFeatures

CustomNormalize

Normalize

CustomPredict

Predict

Deconvolution

DeDepthwiseConv2D

Deconvolution

DepthToSpace

DepthToSpace

DepthToSpace

DepthToSpace

DepthwiseConv2dNative

DepthwiseConv2D

Convolution

DepthwiseConv2dNative

DetectionPostProcess

Custom

Div

Div, RealDiv

Div

Div, RealDiv

DivGrad

DropoutGrad

Eltwise

Eltwise

Sum, Max[3]

Elu

ELU

Elu,
NonMaxSuppression

NonMaxSuppressionV3

EluGrad

Equal

Equal

Equal

Equal

ExpFusion

Exp

Exp

Exp

Exp

ExpandDims

ExpandDims

ExpandDims

Fill

Fill

Fill

Flatten

Flatten

FlattenGrad

Floor

flOOR

Floor

Floor

FloorDiv

FloorDiv

FloorDiv

FloorMod

FloorMod

FloorMod

FullConnection

FullyConnected

InnerProduct

FusedBatchNorm

FusedBatchNorm

FusedBatchNorm,
FusedBatchNormV3

GatherNd

GatherND

GatherNd

Gather

Gather

Gather

GatherV2

Greater

Greater

Greater

Greater

GreaterEqual

GreaterEqual

GreaterEqual

GRU

HardTanh

HashtableLookup

HashtableLookup

HSigmoid

Hswish

HardSwish

HswishGrad

InstanceNorm

InstanceNorm

InstanceNormalization

InvertPermutation

InvertPermutation

L2Norm

L2_NORMALIZATION

LayerNorm

LayerNormGrad

LeakyReLU

LeakyRelu

LeakyRelu

LeakyRelu

LeakyReLUGrad

Less

Less

Less

Less

LessEqual

LessEqual

LessEqual

LRN

LocalResponseNorm

Lrn, LRN

Log

Log

Log

Log

LogGrad

LogicalAnd

LogicalAnd

And

LogicalAnd

LogicalNot

LogicalNot

Not

LogicalNot

LogicalOr

LogicalOr

Or

LogicalOr

LogSoftmax

LogSoftmax

LogSoftmax

LshProjection

LshProjection

LSTM

LSTM

MatMul

BatchMatMul

MatMul,
Gemm

MatMul,
BatchMatMul,
BatchMatMulV2

MatMulGrad

Maximum

Maximum

Max

Maximum

MaximumGrad

MaxPool

MaxPooling

Pooling

MaxPool,
GlobalMaxPool

MaxPool

MaxPoolGrad

Merge

Merge

Minimum

Minimum

Min

Minimum

MinimumGrad

Mul

Mul

Mul

Mul

MulGrad

Neg

Neg

Neg

Neg

NegGrad

NotEqual

NotEqual

NotEqual

OneHot

OneHot

OneHot

OneHot

Pad

Pad, MirrorPad, PadV2

Pad

MirrorPad, Pad, PadV2

Pow

Pow

Power

Pow[2]

Pow

PowGrad

PReLU

PRELU

PReLU

PRelu

QuantDTypeCast

RaggedRange

RaggedRange

RandomStandardNormal

RandomStandardNormal

RandomUniform

RandomUniform

Range

Range

Range

Range

Rank

Rank

Rank

RealDiv

Reciprocal

Reciprocal

ReduceAll

All

ReduceASum

Reduction

ReduceMax

ReduceMax

ReduceMax

Max

ReduceMean

Mean

Reduction

ReduceMean

Mean

ReduceMin

ReduceMin

ReduceMin

Min

ReduceProd

ReduceProd

ReduceProd

Prod

ReduceSum

Sum

Reduction

ReduceSum

Sum

ReduceSumSquare

Reduction

ReduceSumSquare

ReLU

Relu

ReLU

Relu

Relu

ReLUGrad

ReLU6

Relu6

ReLU6

Clip[1]

Relu6

ReLU6Grad

Reshape

Reshape

Reshape

Reshape,
Flatten

Reshape

Resize

ResizeBilinear,
NearestNeighbor

Interp

Resize, Upsample

ResizeBilinear,
ResizeBicubic,
ResizeNearestNeighbor

ResizeGrad

ResizeNearestNeighbor

Reverse

reverse

ReverseV2

ReverseSequence

ReverseSequence

ReverseSequence

Round

Round

Round

Round

Rsqrt

Rsqrt

Rsqrt

Select

Select

Selu

Selu

Scale

Scale

ScatterNd

ScatterNd

ScatterND

ScatterNdUpdate

ScatterNdUpdate

ScatterNdUpdate

Shape

Shape

Shape

Shape

Sigmoid

Logistic

Sigmoid

Sigmoid

Sigmoid

SigmoidGrad

Sin

Sin

Sin

Sin

Size

Size

Slice

Slice

Slice

Slice

Slice

SkipGram

SKipGram

Softmax

Softmax

Softmax

Softmax

Softmax

SoftmaxGrad

Softplus

Softplus

SpaceToBatch

SpaceToBatch

SpaceToBatchND

SpaceToBatchND

SpaceToBatchND

SpaceToDepth

SpaceToDepth

SpaceToDepth

SparseToDense

SpareToDense

Splice

Splice

Split

Split, SplitV

Split

Split, SplitV

SplitWithOverlap

Sqrt

Sqrt

Sqrt

Sqrt

Square

Square

Square

SquaredDifference

SquaredDifference

SquaredDifference

Squeeze

Squeeze

Squeeze

Squeeze

StridedSlice

StridedSlice

Slice,
DynamicSlice

StridedSlice

StridedSliceGrad

Stack

Stack

Pack

Sub

Sub

Sub

Sub

SubGrad

Swish

Switch

Switch

Tanh

Tanh

TanH

Tanh, Sign

Tanh

TanhGrad

TensorListFromTensor

TensorListFromTensor

TensorListGetItem

TensorListGetItem

TensorListReserve

TensorListReserve

TensorListSetItem

TensorListSetItem

TensorListStack

TensorListStack

Tile

Tile

Tile

Tile

Tile

TopK

TopKV2

TopK

TopKV2

Transpose

Transpose

Permute

Transpose, Int8Transpose

Transpose

UniformReal

Unique

Unique

UnsortedSegmentSum

UnsortedSegmentSum

Unsqueeze

Unsqueeze

Unstack

Unstack

Upsample

Where

Where

NonZero, Where

Where

ZerosLike

ZerosLike

ZerosLike

转换工具支持的其他算子[4]

Constant,
Atan, Asin, Tan, Erf,
Loop, Dropout, If, Identity,
Int8GivenIntTensorFill,
Int8GivenTensorFill,
Int8Quantize,
Int8Dequantize,
LpNormalization

Dropout, Enter,
Exit, If,
IsFinite,
LinSpace,
LoopCond,
NextIteration,
StatelessIf,
StatelessWhile,
TensorArrayGatherV3,
TensorArrayReadV3,
TensorArrayScatterV3,
TensorArraySizeV3,
TensorArrayV3,
TensorArrayWriteV3,
While

[1] Clip:仅支持将clip(0, 6)转换为Relu6。

[2] Pow:仅支持指数为单个常数。

[3] Sum与Max:仅支持输入个数为2。

[4] 转换工具支持,但不需要具体实现的算子,一般这类算子在转化工具中被优化而消失,如被融合掉或者使用其他算子代替。