saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-05-23 22:13:38 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Add HardSigmoid to mobile packages. Used by PyTorch MobileNet v3 (#8552)

Browse source
This commit is contained in:
Scott McKay 2021-07-30 12:08:11 +10:00 committed by GitHub
parent 464fd28ee9
commit c6f95841dc
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 6 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
tools/ci_build/github/android/mobile_package.required_operators.config
View file

@ -14,8 +14,8 @@ ai.onnx;12;Abs,Add,And,ArgMax,ArgMin,AveragePool,Cast,Ceil,Clip,Concat,ConstantO
ai.onnx;13;Abs,Add,And,ArgMax,ArgMin,AveragePool,Cast,Ceil,Clip,Concat,ConstantOfShape,Conv,ConvTranspose,Cos,CumSum,DepthToSpace,DequantizeLinear,Div,DynamicQuantizeLinear,Elu,Equal,Exp,Expand,Flatten,Floor,Gather,GatherND,Gemm,Greater,GreaterOrEqual,Identity,If,LRN,LeakyRelu,Less,LessOrEqual,Log,LogSoftmax,Loop,MatMul,Max,MaxPool,Mean,Min,Mul,Neg,NonMaxSuppression,NonZero,Not,Or,PRelu,Pad,Pow,QuantizeLinear,Range,Reciprocal,ReduceMax,ReduceMean,ReduceMin,ReduceProd,ReduceSum,Relu,Reshape,Resize,ReverseSequence,Round,ScatterND,Shape,Sigmoid,Sin,Size,Slice,Softmax,SpaceToDepth,Split,Sqrt,Squeeze,Sub,Sum,Tanh,ThresholdedRelu,Tile,TopK,Transpose,Unique,Unsqueeze,Where
# other ops found in test models
ai.onnx;12;Erf,GlobalAveragePool,InstanceNormalization,MatMulInteger,QLinearConv,QLinearMatMul
ai.onnx;13;Erf,GlobalAveragePool,InstanceNormalization,MatMulInteger,QLinearConv,QLinearMatMul
ai.onnx;12;Erf,GlobalAveragePool,InstanceNormalization,HardSigmoid,MatMulInteger,QLinearConv,QLinearMatMul
ai.onnx;13;Erf,GlobalAveragePool,InstanceNormalization,HardSigmoid,MatMulInteger,QLinearConv,QLinearMatMul
# Control flow ops
# - If and Loop are covered by the tflite converter list
@ -27,6 +27,7 @@ ai.onnx;13;Scan
# Note: LayerNormalization is an internal op even though it is (incorrectly) registered in the ONNX domain.
ai.onnx;1;LayerNormalization
com.microsoft;1;DynamicQuantizeMatMul,FusedConv,FusedGemm,FusedMatMul,Gelu,MatMulIntegerToFloat,NhwcMaxPool,QLinearAdd,QLinearAveragePool,QLinearConv,QLinearGlobalAveragePool,QLinearMul,QLinearSigmoid
# NHWC transformer also uses this, so assuming it's valuable enough to include
com.microsoft;1;QLinearLeakyRelu

4
tools/ci_build/github/android/mobile_package.required_operators.readme.txt
View file

@ -68,9 +68,11 @@ Models from MLPerf Mobile
- ssd_mobilenet_v2_300-qdq.onnx
Other
Mobilenet v2 from pytorch
Mobilenet v2 and v3 from pytorch
- https://pytorch.org/vision/stable/models.html
- pytorch.mobilenet_v2_float.onnx
- pytorch.mobilenet_v2_uint8.onnx
- pytorch.mobilenet_v3_small.onnx
Other assorted pytorch models
- Huggingface mobilebert-uncased (https://huggingface.co/transformers/serialization.html, https://huggingface.co/google/mobilebert-uncased)
- SuperResolution (https://pytorch.org/tutorials/advanced/super_resolution_with_onnxruntime.html)