mirror of
https://github.com/saymrwulf/onnxruntime.git
synced 2026-07-21 19:18:55 +00:00
55278056ad
* Add test for iOS package (#7816) * Add test for iOS package * Add readme * fix pep8 warning * Addressed CR comments, fixed CI failure * Address CR comments * Update readme.md * Update package name and readme, added comments to the podspec * Add podspec template for ios package, update build settings (#7907) * Add podspec template for ios package * minor formatting update * Add spec.source_files for header files * Update spec.public_header_files to spec.source_files * minor update * Add iOS packaging pipeline (#8264) Create a pipeline to produce the iOS package artifacts. * [iOS] Packaging pipeline improvements. (#8324) Updates to the iOS packaging pipeline: - Make it harder to overwrite package archives accidentally when uploading (fails if the archive already exists) - Only upload package archives for release builds - Some clean up * Add metadata_props to ORT model (#8340) * Add metadata_props to ORT model * Minor update * Update python binding, and increase the minimal pipeline size threshold * Fixed a small bug in serializing ir_version * Remove temp ort.py.fbs and add it to .gitignore * Add iOS/macOS static framework (#8357) * Add ability to generate ios static framework * Fix typos * Add pod cache clean, update some comments of previous commit * Fix CI failure with newly added cpuinfo library * Update test model (CoreML requires node has a name) * Addressed CR comments * Fix iOS packaging pipeline failure (#8433) * Fix optimizer crash (#8274) * Update iOS packaging script to default build static framework, disable bitcode (#8533) * default package build to static, disable bitcode * fix pipeline failure * Address CR comments * Add HardSigmoid to mobile packages. Used by PyTorch MobileNet v3 (#8552) * bump the version number to 1.8.2 * Change Windows GPU machine pool to onnxruntime-win-cuda11-0 * [Objective-C API] Fix ORTIsCoreMLExecutionProviderAvailable link error when used from Swift. (#8350) Co-authored-by: Edward Chen <18449977+edgchen1@users.noreply.github.com> Co-authored-by: RandySheriffH <48490400+RandySheriffH@users.noreply.github.com> Co-authored-by: Scott McKay <skottmckay@gmail.com> Co-authored-by: Changming Sun <chasun@microsoft.com>
35 lines
3 KiB
Text
35 lines
3 KiB
Text
# Android package for ORT Mobile operator and type reduction configuration
|
|
#
|
|
# The list of operators was generated from:
|
|
# - the ONNX operators use by the tf2onnx tflite converter
|
|
# - the operators used in a set of tflite models from tfhub, the tflite examples, and the mlperf mobile models
|
|
# - models were optimized with optimizations set to 'basic', 'extended' and 'all'
|
|
# - see the readme file for full details
|
|
|
|
# allow float, int8, uint8. operators that manipulate shapes or indices have int32 and int64 enabled internally.
|
|
!globally_allowed_types;float,int8_t,uint8_t
|
|
|
|
# ops used by the tf2onnx tflite converter. same list for opsets 12 and 13.
|
|
ai.onnx;12;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
|
|
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,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
|
|
# - Scan tends to be used in speech models (it's more efficient than Loop) so include it for support of those
|
|
ai.onnx;12;Scan
|
|
ai.onnx;13;Scan
|
|
|
|
# internal ops added by optimizers
|
|
# 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
|
|
|
|
# Quantized contrib ops that are registered but no usage was found. Excluding for now.
|
|
# com.microsoft;1;DynamicQuantizeLSTM,QAttention
|