SUPPORTED-ONNX-OPS.md

Supported ONNX Operators

Note: some ONNX Ops listed below are pseudo Ops, such as Linear, Conv1d, Conv2d (or other with 1d, 2d suffixes used signify the dimensionality). These are not real ONNX Ops, but are used to represent the corresponding Burn Op.

ONNX OP	Import Support	Burn Support
Abs	✅	✅
Acos	❌	❌
Acosh	❌	❌
Add	✅	✅
And	❌	❌
ArgMax	❌	✅
ArgMin	❌	❌
Asin	❌	❌
Asinh	❌	❌
Atan	❌	❌
Atanh	❌	❌
AveragePool1d	✅	✅
AveragePool2d	✅	✅
BatchNormalization	✅	✅
Bernoulli	❌	❌
BitShift	❌	❌
BitwiseAnd	❌	❌
BitwiseNot	❌	❌
BitwiseOr	❌	❌
BitwiseXor	❌	❌
BlackmanWindow	❌	❌
Cast	✅	✅
CastLike	❌	❌
Ceil	❌	❌
Celu	❌	❌
CenterCropPad	❌	❌
Clip	✅	✅
Col2Im	❌	❌
Compress	❌	❌
Concat	✅	✅
ConcatFromSequence	❌	❌
Constant	✅	✅
ConstantOfShape	❌	❌
Conv1d	✅	✅
Conv2d	✅	✅
ConvInteger	❌	❌
ConvTranspose1d	❌	✅
ConvTranspose2d	✅	✅
Cos	✅	✅
Cosh	❌	❌
CumSum	❌	❌
DepthToSpace	❌	❌
DequantizeLinear	❌	❌
Det	❌	❌
DFT	❌	❌
Div	✅	✅
Dropout	✅	✅
DynamicQuantizeLinear	❌	❌
Einsum	❌	❌
Elu	❌	❌
Equal	✅	✅
Erf	✅	✅
Exp	✅	✅
Expand	❌	✅
EyeLike	❌	❌
Flatten	✅	✅
Floor	❌	❌
Gather	❌	✅
GatherElements	✅	✅
GatherND	❌	❌
Gelu	✅	✅
Gemm	❌	❌
GlobalAveragePool	✅	✅
GlobalLpPool	❌	❌
GlobalMaxPool	❌	❌
Greater	✅	✅
GreaterOrEqual	✅	✅
GridSample	❌	❌
GroupNormalization	❌	✅
GRU	❌	✅
HammingWindow	❌	❌
HannWindow	❌	❌
Hardmax	❌	❌
HardSigmoid	❌	❌
HardSwish	❌	❌
Identity	✅	✅
If	❌	✅
Im	❌	❌
InstanceNormalization	❌	✅
IsInf	❌	❌
IsNaN	❌	❌
LayerNormalization	✅	✅
LeakyRelu	✅	✅
Less	✅	✅
LessOrEqual	✅	✅
Linear	✅	✅
Log	✅	✅
LogSoftmax	✅	✅
Loop	❌	❌
LpNormalization	❌	❌
LpPool	❌	❌
LRN	❌	❌
LSTM	❌	✅
MatMul	✅	✅
MatMulInteger	❌	✅
Max	✅	✅
MaxPool1d	✅	✅
MaxPool2d	✅	✅
MaxRoiPool	❌	❌
MaxUnpool	❌	❌
Mean	❌	✅
MeanVarianceNormalization	❌	❌
MelWeightMatrix	❌	❌
Min	✅	✅
Mish	❌	❌
Mod	❌	❌
Mul	✅	✅
Multinomial	❌	❌
Neg	✅	✅
NegativeLogLikelihoodLoss	❌	❌
NonMaxSuppression	❌	❌
NonZero	❌	❌
Not	✅	✅
OneHot	❌	✅
Optional	❌	❌
OptionalGetElement	❌	❌
OptionalHasElement	❌	❌
Or	❌	❌
Pad	❌	✅
Pow	✅	✅
PRelu	✅	✅
QLinearConv	❌	❌
QLinearMatMul	❌	❌
QuantizeLinear	❌	❌
RandomNormal	✅	✅
RandomNormalLike	❌	✅
RandomUniform	✅	✅
RandomUniformLike	❌	✅
Range	❌	✅
Reciprocal	✅	✅
ReduceL	❌	❌
ReduceLogSum	❌	❌
ReduceLogSumExp	❌	❌
ReduceMax	✅	✅
ReduceMean	✅	✅
ReduceMin	❌	✅
ReduceProd	❌	✅
ReduceSum	✅	✅
ReduceSumSquare	❌	❌
Relu	✅	✅
Reshape	✅	✅
Resize	❌	✅
ReverseSequence	❌	❌
RNN	❌	✅
RoiAlign	❌	❌
Round	❌	❌
Scan	❌	❌
Scatter	❌	✅
ScatterElements	❌	❌
ScatterND	❌	❌
Selu	❌	❌
SequenceAt	❌	❌
SequenceConstruct	❌	❌
SequenceEmpty	❌	❌
SequenceErase	❌	❌
SequenceInsert	❌	❌
SequenceLength	❌	❌
SequenceMap	❌	❌
Shape	✅	✅
Shrink	❌	❌
Sigmoid	✅	✅
Sign	✅	✅
Sin	✅	✅
Sinh	❌	❌
Size	❌	❌
Slice	❌	✅
Softmax	✅	✅
SoftmaxCrossEntropyLoss	❌	❌
Softplus	❌	❌
Softsign	❌	❌
SpaceToDepth	❌	❌
Split	❌	❌
SplitToSequence	❌	❌
Sqrt	✅	✅
Squeeze	✅	✅
STFT	❌	❌
StringNormalizer	❌	❌
Sub	✅	✅
Sum	❌	✅
Tan	❌	❌
Tanh	✅	✅
TfIdfVectorizer	❌	❌
ThresholdedRelu	❌	❌
Tile	❌	✅
TopK	❌	✅
Transpose	✅	✅
Trilu	❌	✅
Unique	❌	❌
Upsample	❌	❌
Where	✅	✅
Xor	❌	❌
Unsqueeze	✅	✅