Skip to content

Latest commit

 

History

History
178 lines (155 loc) · 5.59 KB

File metadata and controls

178 lines (155 loc) · 5.59 KB

Backend Operator Support Report

This file is generated from converter sources by scripts/generate_backend_operator_report.py. Do not edit this file manually. Run make docs-backend-ops after backend changes.

ONNX Runtime Backend

  • Converter source: src/converters/onnx.rs
  • Executor source: src/executors/onnx.rs
  • Converter operator count: 0
  • Executor operator count: 0

Converter Operators

  • (none)

Executor Operators

Executor-level operator coverage follows converter coverage for this backend.

  • (none)

CoreML MLProgram Backend

  • Converter source: src/converters/coreml_mlprogram.rs
  • Executor source: src/executors/coreml.rs
  • Converter operator count: 88
  • Executor operator count: 88

Converter Operators

  • abs, hardSigmoid, reducemin
  • add, hardSwish, reduceproduct
  • argMax, identity, reducesum
  • argMin, instanceNormalization, reducesumsquare
  • averagePool2d, layerNormalization, relu
  • batchNormalization, leakyRelu, reshape
  • cast, lesser, reverse
  • ceil, lesserOrEqual, roundEven
  • clamp, log, scatterElements
  • concat, logicalAnd, scatterND
  • conv2d, logicalNot, sigmoid
  • convTranspose2d, logicalOr, sign
  • cos, logicalXor, sin
  • cumulativeSum, matmul, slice
  • dequantizeLinear, max, softmax
  • div, maxPool2d, softplus
  • elu, min, softsign
  • equal, mul, split
  • erf, neg, sqrt
  • exp, pad, squeeze
  • expand, pow, sub
  • floor, prelu, tan
  • gather, quantizeLinear, tanh
  • gatherElements, reciprocal, tile
  • gelu, reducel1, transpose
  • gemm, reducel2, triangular
  • globalAveragePool, reducelogsum, unsqueeze
  • globalMaxPool, reducelogsumexp, where
  • greater, reducemax
  • greaterOrEqual, reducemean

Executor Operators

Executor-level operator coverage follows converter coverage for this backend.

  • abs, hardSigmoid, reducemin
  • add, hardSwish, reduceproduct
  • argMax, identity, reducesum
  • argMin, instanceNormalization, reducesumsquare
  • averagePool2d, layerNormalization, relu
  • batchNormalization, leakyRelu, reshape
  • cast, lesser, reverse
  • ceil, lesserOrEqual, roundEven
  • clamp, log, scatterElements
  • concat, logicalAnd, scatterND
  • conv2d, logicalNot, sigmoid
  • convTranspose2d, logicalOr, sign
  • cos, logicalXor, sin
  • cumulativeSum, matmul, slice
  • dequantizeLinear, max, softmax
  • div, maxPool2d, softplus
  • elu, min, softsign
  • equal, mul, split
  • erf, neg, sqrt
  • exp, pad, squeeze
  • expand, pow, sub
  • floor, prelu, tan
  • gather, quantizeLinear, tanh
  • gatherElements, reciprocal, tile
  • gelu, reducel1, transpose
  • gemm, reducel2, triangular
  • globalAveragePool, reducelogsum, unsqueeze
  • globalMaxPool, reducelogsumexp, where
  • greater, reducemax
  • greaterOrEqual, reducemean

TensorRT Backend

  • Converter source: src/converters/trtx.rs
  • Executor source: src/executors/trtx.rs
  • Converter operator count: 99
  • Executor operator count: 99

Converter Operators

  • abs, hardSigmoid, reduceLogSum
  • add, hardSwish, reduceLogSumExp
  • argMax, identity, reduceMax
  • argMin, instanceNormalization, reduceMean
  • averagePool2d, isInfinite, reduceMin
  • batchNormalization, isNaN, reduceProduct
  • cast, l2Pool2d, reduceSum
  • ceil, layerNormalization, reduceSumSquare
  • clamp, leakyRelu, relu
  • concat, lesser, resample2d
  • conv2d, lesserOrEqual, reshape
  • convTranspose2d, linear, reverse
  • cos, log, roundEven
  • cumulativeSum, logicalAnd, scatterElements
  • dequantizeLinear, logicalNot, scatterND
  • div, logicalOr, sigmoid
  • elu, logicalXor, sign
  • equal, lstm, sin
  • erf, lstmCell, slice
  • exp, matmul, softmax
  • expand, max, softplus
  • floor, maxPool2d, softsign
  • gather, min, split
  • gatherElements, mul, sqrt
  • gatherND, neg, squeeze
  • gelu, notEqual, sub
  • gemm, pad, tan
  • globalAveragePool, pow, tanh
  • globalMaxPool, prelu, tile
  • greater, quantizeLinear, transpose
  • greaterOrEqual, reciprocal, triangular
  • gru, reduceL1, unsqueeze
  • gruCell, reduceL2, where

Executor Operators

Executor-level operator coverage follows converter coverage for this backend.

  • abs, hardSigmoid, reduceLogSum
  • add, hardSwish, reduceLogSumExp
  • argMax, identity, reduceMax
  • argMin, instanceNormalization, reduceMean
  • averagePool2d, isInfinite, reduceMin
  • batchNormalization, isNaN, reduceProduct
  • cast, l2Pool2d, reduceSum
  • ceil, layerNormalization, reduceSumSquare
  • clamp, leakyRelu, relu
  • concat, lesser, resample2d
  • conv2d, lesserOrEqual, reshape
  • convTranspose2d, linear, reverse
  • cos, log, roundEven
  • cumulativeSum, logicalAnd, scatterElements
  • dequantizeLinear, logicalNot, scatterND
  • div, logicalOr, sigmoid
  • elu, logicalXor, sign
  • equal, lstm, sin
  • erf, lstmCell, slice
  • exp, matmul, softmax
  • expand, max, softplus
  • floor, maxPool2d, softsign
  • gather, min, split
  • gatherElements, mul, sqrt
  • gatherND, neg, squeeze
  • gelu, notEqual, sub
  • gemm, pad, tan
  • globalAveragePool, pow, tanh
  • globalMaxPool, prelu, tile
  • greater, quantizeLinear, transpose
  • greaterOrEqual, reciprocal, triangular
  • gru, reduceL1, unsqueeze
  • gruCell, reduceL2, where