You are viewing an old version of this page. View the current version.

Compare with Current View Page History

« Previous Version 16 Next »

Introduction:

This page tracks the current status and development  to support ONNX  on Mxnet. We currently support:

  • import of ONNX models into Mxnet.
  • export MXNet models to ONNX format.


ONNX-MXNET Import Module

We have two repositories for the import module:

  1. onnx-mxnet repository inside onnx https://github.com/onnx/onnx-mxnet  (deprecated)
  2. A newly created and refactored module inside Mxnet -> contrib. https://github.com/apache/incubator-mxnet/tree/master/python/mxnet/contrib/onnx/onnx2mx


MXNET-ONNX Export module

A new module has been added to MXNet repository to export MXNet models to ONNX model format. https://github.com/apache/incubator-mxnet/tree/master/python/mxnet/contrib/onnx/mx2onnx

Operator Coverage:

This table keeps track of the status of all ONNX operators supported by Mxnet.
ONNX backend test script reports the coverage on the operators and attributes.


Status meaning:

OK = currently we support the operator

OK, in review = PR is out, waiting for tomorrow’s meeting and feedback

NOT OK, under development = Operator is missing on MXNet backend or direct 1:1 mapping doesn’t exist

NOT OK = Not supported right now


OperatorTest CoverageMxnet (Import)Mxnet (Export)
AbsYesOKOK
Acos
OK, In review
AddYesOKOK
AndYes 

OK


ArgMaxYesOKOK
ArgMinYes OKOK
Asin
OK, In review
Atan
OK, In review
AveragePoolYesOKOK
BatchNormalizationYesOKOK
CastYesOKOK
CeilYes OKOK
ClipYesOK
ConcatYesOKOK
ConstantYesOK
ConvYesOKOK
ConvTransposeYes OKOK
Cos
OK, In review
DepthToSpace
NOT OK, under development
DivYesOKOK
Dropout YesOKOK
EluYesOKOK
EqualYesOK
ExpYesOKOK
FlattenYesPARTIAL, only supports default axis=1OK
Floor YesOKOK
GRU
NOT OK , under development
GatherYesOK
GemmYesOKOK
GlobalAveragePoolYesOKOK
GlobalLpPool YesOK, In review
GlobalMaxPoolYesOKOK
Greater YesOK
HardSigmoid YesOK
Hardmax YesOK, In review
Identity
NOT OK
InstanceNormalization YesOK, In review
LRNYes OKOK
LSTM
NOT OK, under development
LeakyReluYesOKOK
LessYes OK
LogYesOKOK
LogSoftMaxYes OK
LpNormalization OK, In reviewOK
LpPoolYesOK, In review
MatMul
OK, In review
MaxYesOKOK
MaxPoolYesOKOK
MaxRoiPoolYes OK, In review
MeanYes OKOK
MinYesOKOK
MulYesOKOK
Multinomial
OK, In review
NegYesOKOK
NotYes OK
OrYes OK
PReluYesOKOK
PadYesOKOK
PowYesPartial, only supports default axis=1OK
RNN NOT OK, under development
RandomNormalYes OK
RandomNormalLikeYes OK
RandomUniformYes OK
RandomUniformLikeYes OK
ReciprocalYes OKOK
ReduceL1Yes OK
ReduceL2 YesOK
ReduceLogSum YesOK
ReduceLogSumExp YesOK
ReduceMaxYesOKOK
ReduceMeanYesOKOK
ReduceMinYesOKOK
ReduceProdYesOKOK
ReduceSumYesOK
ReduceSumSquareYes OK
ReluYesOKOK
ReshapeYesOKOK
SeluYesNOT OK, under developmentOK
Shape
OK, In review
SigmoidYesOKOK
Sin
OK, In review
Size
OK, In review
SliceYesPartial, supports axis=1OK
SoftmaxYesOKOK
SoftplusYesOKOK
Softsign YesOKOK
SpaceToDepth NOT OK, under development
SplitYesOKOK
SqrtYes OKOK
SqueezeYesOKOK
SubYesOKOK
SumYesOKOK
Tan
OK, In review
TanhYesOKOK
Tile YesOK
TopK
OK, In review
TransposeYesOKOK
UnsqueezeYesOK, In reviewOK
Upsample
OK, In review
XorYes OK
experimental ATen NOT OK
experimental Affine NOT OK
experimental ConstantFill NOT OK
experimental Crop NOT OK
experimental GRUUnit NOT OK
experimental GivenTensorFill NOT OK
experimental If NOT OK
experimental ImageScaler YesOK, In review
experimental Loop
NOT OK
experimental LoopIndex
NOT OK
experimental MeanVarianceNormalization NOT OK
experimental ParametricSoftplus NOT OK
experimental Scale NOT OK
experimental ScaledTanh NOT OK
experimental ThresholdedRelu NOT OK

 

ONNX models coverage:

ONNX backend tests include below models. The table lists current status on Mxnet:

 

ONNX ModelsMxnet Support
bvlc_alexnetOK
densenet121OK
inception_v1OK, In review
inception_v2OK, In review
resnet50OK
shufflenetOK, In review
squeezenetOK
vgg16OK
vgg19OK
bvlc_googlenetOK
bvlc_caffenetOK
bvlc-rcnn-ilsvrc13OK

 

 

 

 

 

 

 

 

 

 

 

  • No labels