...
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:
- onnx-mxnet repository inside onnx https://github.com/onnx/onnx-mxnet (deprecated)
- A newly created and refactored module inside Mxnet -> contrib. https://github.com/apache/incubator-mxnet/tree/master/python/mxnet/contrib/onnx/_importonnx2mx
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
NOT OK, under development = Operator is missing on MXNet backend or direct 1:1 mapping doesn’t exist
NOT OK = Not supported right now
Operator | Test Coverage | Mxnet (Import) | Mxnet (Export) | ||
---|---|---|---|---|---|
Abs | Yes | OK | OK | ||
Acos | Yes | OK | OK | ||
Add | Yes | OK | OK | ||
And | Yes | OK | OK | ||
ArgMax | Yes | OK | OK | ||
ArgMin | Yes | OK | OK | ||
Asin | Yes | OK | OK | ||
Atan | Yes | OK | Ok | ||
AveragePool | Yes | OK | OK | ||
BatchNormalization | Yes | OK | OK | ||
Cast | Yes | OK | OK | ||
Ceil | Yes | OK | OK | ||
Clip | Yes | OK | NOT OK, under development | ||
Concat | Yes | OK | OK | ||
Constant | Yes | NOT OK | |||
Conv | Yes | OK | OK | ||
ConvTranspose | Yes | OK | OK | ||
Cos | Yes | OK | OK | ||
Crop | OK | ||||
DepthToSpace | Yes | OK | NOT OK, under development | ||
Div | Yes | OK | OK | ||
Dropout | Yes | OK | OK | ||
Elu | Yes | OK | OK | ||
Equal | Yes | OK | NOT OK | ||
Exp | Yes | OK | OK | ||
Flatten | Yes | PARTIAL, only supports default axis=1 | OK | ||
Floor | Yes | OK | OK | ||
GRU | NOT OK , under development | ||||
Gather | Yes | NOT OK, under development | |||
Gemm | Yes | OK | OK | ||
GlobalAveragePool | Yes | OK | OK | ||
GlobalLpPool | Yes | OK | NOT OK, under development | ||
GlobalMaxPool | Yes | OK | OK | ||
Greater | Yes | OK | NOT OK, under development | ||
HardSigmoid | Yes | OK | NOT OK, under development | ||
Hardmax | Yes | OK | NOT OK, under development | ||
Identity | NOT OK | OK | |||
If | |||||
InstanceNormalization | Yes | OK | NOT OK, under development | ||
LRN | Yes | OK | OK | ||
LSTM | NOT OK, under development | ||||
LeakyRelu | Yes | OK | OK | ||
Less | Yes | OK | NOT OK, under development | ||
Log | Yes | OK | OK | ||
LogSoftMax | Yes | OK | NOT OK, under development | ||
Loop | |||||
LpNormalization | Yes | NOT OK, under development | |||
LpPool | Yes | NOT OK, under development | |||
LpPoolMatMul | Yes | OK | OK | ||
Max | Yes | OK | OK | ||
MaxPool | Yes | OK | OK | ||
MaxRoiPool | Yes | OK | NOT OK, under development | ||
Mean | Yes | OK | NOT OK, under development | ||
Min | Yes | OK | OK | ||
Mul | Yes | OK | OK | ||
Multinomial | Yes | OK | OK | ||
Neg | Yes | OK | OK | ||
Not | Yes | OK | NOT OK, under development | ||
Or | Yes | OK | NOT OK, under development | ||
PRelu | Yes | OK | OK | ||
Pad | Yes | OK | OK | ||
Pow | Yes | Partial, only supports default axis=1 | OK | ||
RNN | NOT OK, under development | ||||
RandomNormal | Yes | OK | OK | ||
RandomNormalLike | Yes | OK | OK | ||
RandomUniform | Yes | OK | OK | ||
RandomUniformLike | Yes | OK | OK | ||
Reciprocal | Yes | OK | OK | ||
ReduceL1 | Yes | OK | NOT OK, under development | ||
ReduceL2 | Yes | OK | NOT OK, under development | ||
ReduceLogSum | Yes | OK | NOT OK, under development | ||
ReduceLogSumExp | Yes | OK | NOT OK, under development | ||
ReduceMax | Yes | OK | OK | ||
ReduceMean | Yes | OK | OK | ||
ReduceMin | Yes | OK | OK | ||
ReduceProd | Yes | OK | OK | ||
ReduceSum | Yes | OK | OK | ||
ReduceSumSquare | Yes | OK | NOT OK, under development | ||
Relu | Yes | OK | OK | ||
Reshape | Yes | OK | OK | ||
Selu | Yes | NOT OK, under development | OK | OK | |
Shape | OK | OK | |||
Sigmoid | Yes | OK | OK | ||
SinSigmoid | Yes | OK | OK | ||
SizeSlice | Yes | OK | NOT OK, under development | ||
SoftmaxSlice | Yes | PARTIALPartial, only supports default axis=1 | OK | ||
Softmax | Yes | OK | OK | ||
Softplus | Yes | OK | NOT OK, under development | ||
Softsign | Yes | OK | NOT OK, under development | ||
SpaceToDepth | Yes | OK | NOT OK, under development | ||
Split | Yes | OK | NOT OK, under development | ||
Sqrt | Yes | OK | OK | ||
Squeeze | Yes | OK | OK | ||
Sub | Yes | OK | OK | ||
Sum | Yes | OK | OK | ||
Tan | Yes | OK | OK | ||
Tanh | Yes | OK | OK | ||
Tile | Yes | NOT OK, under development | NOT OK, under development | ||
TopK | Yes | OK, in review | OK, in review | ||
Transpose | Yes | OK | OK | ||
XorUnsqueeze | Yes | NOT OK, under development | |||
experimental ATen | NOT OK, under development | ||||
experimental Affine | NOT OK, under development | ||||
experimental ConstantFill | NOT OK, under development | ||||
experimental Crop | NOT OK, under development | ||||
experimental FC | NOT OK, under development | ||||
experimental GRUUnit | NOT OK, under development | ||||
experimental GivenTensorFill | NOT OK, under development | ||||
experimental Identity | NOT OK, under development | ||||
experimental ImageScaler | NOT OK, under development | ||||
experimental MeanVarianceNormalization | NOT OK, under development | ||||
experimental ParametricSoftplus | NOT OK, under development | ||||
experimental Scale | NOT OK, under development | ||||
experimental ScaledTanh | NOT OK, under development | ||||
experimental ThresholdedRelu | NOT OK, under development | ||||
experimental Upsample | NOT OK, under development |
In review | OK | ||
Upsample | Yes | OK, in review | OK, in review |
Xor | Yes | OK | OK |
experimental ATen | NOT OK | ||
experimental Affine | NOT OK | ||
experimental ConstantFill | NOT OK | ||
experimental GRUUnit | NOT OK | ||
experimental GivenTensorFill | NOT OK | ||
experimental ImageScaler | Yes | OK, In review | |
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 Models | Mxnet Support |
---|---|
bvlc_alexnet | OK |
densenet121 | OK |
inception_v1 | NOT OK, precision difference due to issue |
inception_v2 | NOT OK, precision difference due to issue |
resnet50 | OK |
shufflenet | NOT OK, precision difference due to issueIn review |
squeezenet | OK |
vgg16 | OK |
vgg19 | OK |
bvlc_googlenet | OK |
bvlc_caffenet | OK |
bvlc-rcnn-ilsvrc13 | OK |
...