Operators Support Table
The following table shows ai.onnx operators from which onnx opset version are currently supported by ONNX Runtime Web. For example, 4-6, 8+ means ONNX Runtime Web currently support opset version 4 to 6, 8 and above.
See Compatibility for a list of the supported platforms.
This file is automatically generated from the def files via this script. Do not modify directly.
| Operator |
WebGl Backend |
| Abs |
6-12, 13+ |
| Acos |
7+ |
| Acosh |
|
| Add |
7-12, 13, 14+ |
| And |
7+ |
| ArgMax |
|
| ArgMin |
|
| Asin |
7+ |
| Asinh |
|
| Atan |
7+ |
| Atanh |
|
| AveragePool |
7-9, 10, 11+ |
| BatchNormalization |
7-8, 9-13, 14, 15+ |
| Bernoulli |
|
| BitShift |
|
| BlackmanWindow |
|
| Cast |
6-8, 9-12, 13+ |
| CastLike |
|
| Ceil |
6-12, 13+ |
| Celu |
|
| Clip |
6-10, 11, 12, 13+ |
| Compress |
|
| Concat |
4-10, 11-12, 13+ |
| ConcatFromSequence |
|
| Constant |
|
| ConstantOfShape |
|
| Conv |
1-10, 11+ |
| ConvInteger |
|
| ConvTranspose |
1-10, 11+ |
| Cos |
7+ |
| Cosh |
|
| CumSum |
|
| DFT |
|
| DepthToSpace |
1-10, 11-12, 13+ |
| DequantizeLinear |
|
| Det |
|
| Div |
7-12, 13, 14+ |
| Dropout |
7-9, 10-11, 12, 13+ |
| DynamicQuantizeLinear |
|
| Einsum |
|
| Elu |
6+ |
| Equal |
7-10, 11-12, 13+ |
| Erf |
|
| Exp |
6-12, 13+ |
| Expand |
|
| EyeLike |
|
| Flatten |
1-8, 9-10, 11-12, 13+ |
| Floor |
6-12, 13+ |
| GRU |
|
| Gather |
1-10, 11-12, 13+ |
| GatherElements |
|
| GatherND |
|
| Gemm |
7-8, 9-10, 11-12, 13+ |
| GlobalAveragePool |
1+ |
| GlobalLpPool |
|
| GlobalMaxPool |
1+ |
| Greater |
7-8, 9-12, 13+ |
| GreaterOrEqual |
|
| GridSample |
|
| HammingWindow |
|
| HannWindow |
|
| HardSigmoid |
|
| HardSwish |
|
| Hardmax |
|
| Identity |
1-12, 13, 14-15, 16+ |
| If |
|
| InstanceNormalization |
6+ |
| IsInf |
|
| IsNaN |
|
| LRN |
|
| LSTM |
|
| LayerNormalization |
|
| LeakyRelu |
6-15, 16+ |
| Less |
7-8, 9-12, 13+ |
| LessOrEqual |
|
| Log |
6-12, 13+ |
| LogSoftmax |
|
| Loop |
|
| LpNormalization |
|
| LpPool |
|
| MatMul |
1-8, 9-12, 13+ |
| MatMulInteger |
|
| Max |
|
| MaxPool |
1-7, 8-9, 10, 11, 12+ |
| MaxRoiPool |
|
| MaxUnpool |
|
| Mean |
|
| MeanVarianceNormalization |
|
| MelWeightMatrix |
|
| Min |
|
| Mod |
|
| Mul |
7-12, 13, 14+ |
| Multinomial |
|
| Neg |
6-12, 13+ |
| NegativeLogLikelihoodLoss |
|
| NonMaxSuppression |
|
| NonZero |
|
| Not |
1+ |
| OneHot |
|
| Optional |
|
| OptionalGetElement |
|
| OptionalHasElement |
|
| Or |
7+ |
| PRelu |
7-8, 9-15, 16+ |
| Pad |
2-10, 11-12, 13+ |
| Pow |
7-11, 12, 13-14, 15+ |
| QLinearConv |
|
| QLinearMatMul |
|
| QuantizeLinear |
|
| RNN |
|
| RandomNormal |
|
| RandomNormalLike |
|
| RandomUniform |
|
| RandomUniformLike |
|
| Range |
|
| Reciprocal |
|
| ReduceL1 |
|
| ReduceL2 |
|
| ReduceLogSum |
1-10, 11-12, 13+ |
| ReduceLogSumExp |
|
| ReduceMax |
1-10, 11, 12, 13+ |
| ReduceMean |
1-10, 11-12, 13+ |
| ReduceMin |
1-10, 11, 12, 13+ |
| ReduceProd |
1-10, 11-12, 13+ |
| ReduceSum |
1-10, 11-12 |
| ReduceSumSquare |
1-10, 11-12, 13+ |
| Relu |
6-12, 13, 14+ |
| Reshape |
5-12, 13, 14+ |
| Resize |
10, 11-12, 13+ |
| ReverseSequence |
|
| RoiAlign |
|
| Round |
|
| STFT |
|
| Scan |
|
| Scatter |
|
| ScatterElements |
|
| ScatterND |
|
| Selu |
|
| SequenceAt |
|
| SequenceConstruct |
|
| SequenceEmpty |
|
| SequenceErase |
|
| SequenceInsert |
|
| SequenceLength |
|
| SequenceMap |
|
| Shape |
1-12, 13-14, 15+ |
| Shrink |
|
| Sigmoid |
6-12, 13+ |
| Sign |
|
| Sin |
7+ |
| Sinh |
|
| Size |
|
| Slice |
1-9, 10, 11-12, 13+ |
| Softmax |
1-10, 11-12, 13+ |
| SoftmaxCrossEntropyLoss |
|
| Softplus |
|
| Softsign |
|
| SpaceToDepth |
|
| Split |
2-10, 11-12 |
| SplitToSequence |
|
| Sqrt |
6-12, 13+ |
| Squeeze |
1-10, 11-12, 13+ |
| StringNormalizer |
|
| Sub |
7-12, 13, 14+ |
| Sum |
6-7, 8-12, 13+ |
| Tan |
7+ |
| Tanh |
6-12, 13+ |
| TfIdfVectorizer |
|
| ThresholdedRelu |
|
| Tile |
6-12, 13+ |
| TopK |
|
| Transpose |
1-12, 13+ |
| Trilu |
|
| Unique |
|
| Unsqueeze |
1-10, 11-12, 13+ |
| Upsample |
7-8, 9 |
| Where |
|
| Xor |
7+ |
148b1efe5e