operators.md

Operators Support Table

The following table shows ai.onnx operators from which onnx opset version are currently supported by onnxjs. For example, 4-6, 8+ means ONNX.js 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	Cpu Backend	Wasm Backend	WebGl Backend
Abs	6+		6+
Acos	7+		7+
Acosh	9+
Add	7+	7+	7+
And	7+	7+	7+
ArgMax	1+
ArgMin
Asin	7+		7+
Asinh	9+
Atan	7+		7+
Atanh	9+
AveragePool	7-9, 10+	7-9, 10+	7-9, 10+
BatchNormalization	7-8, 9+	7-8, 9+	7-8, 9+
Cast
Ceil	6+		6+
Clip	6+	6+	6+
Compress
Concat	4+		4+
Constant
ConstantOfShape
Conv	1+	1+	1+
ConvInteger
ConvTranspose
Cos	7+		7+
Cosh	9+
DepthToSpace
DequantizeLinear
Div	7+	7+	7+
Dropout	7-9, 10+		7-9, 10+
Elu	6+		6+
Equal			7+
Erf
Exp	6+		6+
Expand
EyeLike
Flatten	1-8, 9+		1-8, 9+
Floor	6+		6+
GRU
Gather	1+		1+
Gemm	7-8, 9+	7-8, 9+	7-8, 9+
GlobalAveragePool	1+	1+	1+
GlobalLpPool
GlobalMaxPool	1+	1+	1+
Greater			7-8, 9+
HardSigmoid
Hardmax
Identity			1+
If
InstanceNormalization	6+	6+
IsInf
IsNaN	9+
LRN	1+
LSTM
LeakyRelu	6+		6+
Less			7-8, 9+
Log	6+		6+
LogSoftmax
Loop
LpNormalization
LpPool
MatMul	1-8, 9+	1-8, 9+	1-8, 9+
MatMulInteger
Max
MaxPool	1-7, 8-9, 10+	1-7, 8-9, 10+	1-7, 8-9, 10+
MaxRoiPool
MaxUnpool
Mean
MeanVarianceNormalization
Min
Mod
Mul	7+	7+	7+
Multinomial
Neg	6+		6+
NonMaxSuppression
NonZero
Not	1+		1+
OneHot
Or	7+	7+	7+
PRelu	7-8, 9+	7-8, 9+	7-8, 9+
Pad			2+
Pow			7+
QLinearConv
QLinearMatMul
QuantizeLinear
RNN
RandomNormal
RandomNormalLike
RandomUniform
RandomUniformLike
Reciprocal	6+
ReduceL1
ReduceL2
ReduceLogSum	1+		1+
ReduceLogSumExp
ReduceMax	1+		1+
ReduceMean	1+		1+
ReduceMin	1+		1+
ReduceProd	1+		1+
ReduceSum	1+		1+
ReduceSumSquare	1+		1+
Relu	6+		6+
Reshape	5+		5+
Resize
ReverseSequence
RoiAlign
Scan
Scatter
Selu
Shape
Shrink
Sigmoid	6+		6+
Sign	9+
Sin	7+		7+
Sinh	9+
Size
Slice	1-9, 10+		1-9, 10+
Softmax	1+	1+	1+
Softplus
Softsign
SpaceToDepth
Split			2+
Sqrt	6+		6+
Squeeze	1+		1+
StringNormalizer
Sub	7+	7+	7+
Sum	6-7, 8+	6-7, 8+	6-7, 8+
Tan	7+		7+
Tanh	6+		6+
TfIdfVectorizer
ThresholdedRelu
Tile	6+		6+
TopK
Transpose	1+		1+
Unsqueeze	1+		1+
Upsample
Where
Xor	7+	7+	7+