saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-05-31 23:27:43 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
onnxruntime/js/web/docs/operators.md
Changming Sun 6cdf071a94
Cherry-picks to the release branch (#16017) 
### Description
Cherry-picks 26 commits to the release branch. 
Most cherry-picks are clean merges. Except:

1. When I got conflicts in cgmanifest.json and download-deps.yml, I
choose to ignore the conflicts and regenerate the two files
2. There were some conflicts in cmake/deps.txt, onnxruntime_c_api.cc


PR list:

[js/webgpu] fix Transpose with non-float tensor (#15819)
[js/web] fix terser reserved symbols for worker (#15864)
[JSEP] fix constructor for OrtDevice (#15805)
Bump engine.io from 6.4.1 to 6.4.2 in /js/web (#15799)
Bump engine.io from 6.4.0 to 6.4.2 in /onnxruntime/test/wasm (#15798)
[wasm] revert emsdk to v3.1.19 (#15793)
[wasm/JSEP] add threaded build to artifacts (#15777)
[js/web] add target ort.webgpu.min.js (#15780)
update ort extensions to 94142d8391c9791ec71c38336436319a2d4ac7a0 (#15688)
fix: setting builder optimization level to TRT 8.6 default (#15897)
Adust GetVersionString() GetBuildInfoString() signatures and move them to OrtApi (#15921)
Fix segfault for multiple GPU run (regression) (#15823)
android package fix (#15999)
[CoreML EP] Minor changes to allow CoreML EP to handle more nodes and models. (#15993)
Adding support for conv fp16 fusion on Resnet50v1 (#15474)
update onnx release 1.14 for docker files (#15680)
Avoid generating training documentation during packaging (#15795)
Update Conv-Add-Relu Fusion Transformation (#15834)
Fix symbolic shape infer empty value_info (#15842)
NhwcFusedConv: Add before Activation (#15837)
use __hmul2 instead of __hmul2_rn (#15852)
change the EP device to default OrtDevice() for memoryType equals CPU Input (#15903)
Fixing NhwcFusedConv fp16 (#15950)
fix topo sort in quantization tool (#16003)
[doc] add LeakyRelu to coreml supported ops (#15944)
[DML EP] Add frequent upload heap flushing (#15960)

Co-authored-by: Yulong Wang 
Co-authored-by: dependabot[bot] 
Co-authored-by: Guenther Schmuelling 
Co-authored-by: Shalva Mist 
Co-authored-by: Maximilian Müller 
Co-authored-by: Dmitri Smirnov 
Co-authored-by: pengwa 
Co-authored-by: Ashwini Khade 
Co-authored-by: Edward Chen 
Co-authored-by: Jian Chen 
Co-authored-by: liqun Fu 
Co-authored-by: Baiju Meswani 
Co-authored-by: Tianlei Wu 
Co-authored-by: Chen Fu 
Co-authored-by: Ye Wang 
Co-authored-by: cao lei 
Co-authored-by: Yufeng Li 
Co-authored-by: Rachel Guo 
Co-authored-by: Patrice Vignola
2023-05-19 14:04:43 -07:00

30 KiB
Raw Blame History

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, 11-18, 19+
BatchNormalization 7-8, 9-13, 14, 15+
Bernoulli
BitShift
BitwiseAnd
BitwiseNot
BitwiseOr
BitwiseXor
BlackmanWindow
Cast 6-8, 9-12, 13-18, 19+
CastLike
Ceil 6-12, 13+
Celu
CenterCropPad
Clip 6-10, 11, 12, 13+
Col2Im
Compress
Concat 4-10, 11-12, 13+
ConcatFromSequence
Constant
ConstantOfShape
Conv 1-10, 11+
ConvInteger
ConvTranspose 1-10, 11+
Cos 7+
Cosh
CumSum
DFT
DeformConv
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, 13-18, 19+
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
GroupNormalization
HammingWindow
HannWindow
HardSigmoid
HardSwish
Hardmax
Identity 1-12, 13, 14-15, 16-18, 19+
If
InstanceNormalization 6+
IsInf
IsNaN
LRN 1-12, 13+
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
Mish
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, 13-17, 18, 19+
Pow 7-11, 12, 13-14, 15+
QLinearConv
QLinearMatMul
QuantizeLinear
RNN
RandomNormal
RandomNormalLike
RandomUniform
RandomUniformLike
Range
Reciprocal
ReduceL1
ReduceL2
ReduceLogSum 1-10, 11-12, 13-17, 18+
ReduceLogSumExp
ReduceMax 1-10, 11, 12, 13-17, 18+
ReduceMean 1-10, 11-12, 13-17, 18+
ReduceMin 1-10, 11, 12, 13-17, 18+
ReduceProd 1-10, 11-12, 13-17, 18+
ReduceSum 1-10, 11-12
ReduceSumSquare 1-10, 11-12, 13-17, 18+
Relu 6-12, 13, 14+
Reshape 5-12, 13, 14-18, 19+
Resize 10, 11-12, 13-17, 18, 19+
ReverseSequence
RoiAlign
Round
STFT
Scan
Scatter
ScatterElements
ScatterND
Selu
SequenceAt
SequenceConstruct
SequenceEmpty
SequenceErase
SequenceInsert
SequenceLength
SequenceMap
Shape 1-12, 13-14, 15-18, 19+
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+