root
/
MNN
mirror of https://github.com/alibaba/MNN.git
1
0
Fork 0
Code Issues Actions 2 Packages Projects Releases Wiki Activity
MNN/source/backend/cpu/CPUOPRegister.cpp

229 lines
12 KiB
C++
Raw Normal View History

fix register spell
2019-05-08 16:37:43 +08:00
// This file is generated by Shell for ops register
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
namespace MNN {
fix backend/op/sizer register
2019-05-09 19:39:33 +08:00
#ifdef MNN_CODEGEN_REGISTER
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
extern void ___CPUArgMaxCreator__OpType_ArgMax__();
Update
2019-12-27 22:16:57 +08:00
extern void ___CPUArgMaxCreator__OpType_ArgMin__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
extern void ___CPUAsStringCreator__OpType_AsString__();
extern void ___CPUBatchMatMulCreator__OpType_BatchMatMul__();
extern void ___CPUBatchToSpaceNDCreator__OpType_BatchToSpaceND__();
extern void ___CPUBinaryCreator__OpType_BinaryOp__();
Update
2019-12-27 22:16:57 +08:00
extern void ___CPUBroadcastToCreator__OpType_BroadcastTo__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
extern void ___CPUCastCreator__OpType_Cast__();
extern void ___CPUConcatCreator__OpType_Concat__();
extern void ___CPUConstCreator__OpType_Const__();
Update
2019-12-27 22:16:57 +08:00
extern void ___CPUConstCreator__OpType_TrainableParam__();
beta 0.2.0.0 - replace FreeImage with stb_image - warn unicode error in Windows compiling - separate clang/gcc build script for android - add default values in fbs - optimize CPU conv / conv depthwise / deconv / deconv depthwise / lstm / sigmoid - add sub support in eltwise - add reciprocal / log1p / log in unary - add zero like / select / set diff 1d - add batch support for permute - add training codes - fix metal error in dynamic separate storage type handling
2019-06-17 20:10:35 +08:00
extern void ___CPUConv2DBackPropFilterCreator__OpType_Conv2DBackPropFilter__();
beta 0.2.0.3 - add quantization tool & cpu impl & demo/exec - add thread pool - add tests - fix onnx converter tensor name mismatch - optimize cpu performance with SSE for windows
2019-07-11 13:56:52 +08:00
extern void ___CPUConvInt8Creator__OpType_ConvInt8__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
extern void ___ConvolutionFactory__OpType_Convolution__();
- dynamic computation graph (beta) - add supports (/express) - add tests - add benchmarks with it (/benchmark/exprModels) - Python - MNN engine and tools were submitted to pip - available on Windows/macOS/Linux - Engine/Converter - add supports for each op benchmarking - refactor optimizer by separating steps - CPU - add supports for Conv3D, Pool3D, ELU, ReverseSequence - fix ArgMax, Permute, Scale, BinaryOp, Slice, SliceTf - OpenCL - add half transform in CPU - add broadcast supports for binary - optimize Conv2D, Reshape, Eltwise, Gemm, etc. - OpenGL - add sub, real div supports for binary - add supports for unary - optimize Conv2D, Reshape - Vulkan - add max supports for eltwise - Metal - fix metallib missing problem - Train/Quantization - use express to refactor training codes
2019-09-26 21:02:07 +08:00
extern void ___Convolution3DCreator__OpType_Convolution3D__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
extern void ___CPUConvolutionDepthwiseCreator__OpType_ConvolutionDepthwise__();
beta 0.2.0.4 - bug fix for quantization tool - bug fix/performance update for thread pool - bug fix for converters - tutorial/doc update - more op support
2019-07-19 17:09:09 +08:00
extern void ___CPUCosineSimilarityCreator__OpType_CosineSimilarity__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
extern void ___CPUCropCreator__OpType_Crop__();
extern void ___CPUCropAndResizeCreator__OpType_CropAndResize__();
extern void ___CPUDeconvolutionCreator__OpType_Deconvolution__();
extern void ___CPUDeconvolutionDepthwiseCreator__OpType_DeconvolutionDepthwise__();
beta 0.2.0.5 - CPU - add support for DepthToSpace & SpaceToDepth ops - OpenGL - add Android demo - add half / float runtime option - add support for ROIPooling, Squeeze - fix bugs in conv im2col - OpenCL - fix Concat, Eltwise, Reshape bugs - Tools - add KL threshold method in quantization tool - support optimization for graph with multiple rnn
2019-07-25 13:36:35 +08:00
extern void ___DepthToSpaceCreator__OpType_DepthToSpace__();
beta 0.2.0.3 - add quantization tool & cpu impl & demo/exec - add thread pool - add tests - fix onnx converter tensor name mismatch - optimize cpu performance with SSE for windows
2019-07-11 13:56:52 +08:00
extern void ___CPUDepthwiseConvInt8Creator__OpType_DepthwiseConvInt8__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
extern void ___CPUDequantizeCreator__OpType_Dequantize__();
extern void ___CPUDetectionOutputCreator__OpType_DetectionOutput__();
0.2.1.5 # integration - add travis CI - fix building parameters for python # converter - add half storage option for MNN converter - fix op name lost in converter - fix converter bug for print input output, identity remove output # ops - add quantized Convolution & Deconvolution support on OpenCL - add more expression supports - add DetectionPostProcess Op for TensorFlow Lite (ssd is supported directly now) - add supports for LSTM & ELU for ONNX - add support for Convolution that weights is not constant for ONNX - fix Unary Op compile error on Linux - fix Metal backend buffer reuse after resize - fix Metal raw memory access after model releasing - fix redundant transpose in Winograd generater
2019-11-15 14:22:45 +08:00
extern void ___CPUDetectionPostProcessCreator__OpType_DetectionPostProcess__();
Update
2019-12-27 22:16:57 +08:00
extern void ___CPUDilation2DCreator__OpType_Dilation2D__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
extern void ___CPUEltwiesCreator__OpType_Eltwise__();
beta 0.2.0.8 - add NaN check-up - add quantification support for ScaleAdd Op - add binary to eltwise optimization - add console logs for quantization tool - better document for quantization tool - replace redundant dimension flags with dimension format - optimize performance of TensorFlow Lite Quantized Convolution - fix axis support for ONNX softmax - fix get performance compile error on Windows
2019-08-22 20:13:46 +08:00
extern void ___CPUEltwiseInt8Creator__OpType_EltwiseInt8__();
- dynamic computation graph (beta) - add supports (/express) - add tests - add benchmarks with it (/benchmark/exprModels) - Python - MNN engine and tools were submitted to pip - available on Windows/macOS/Linux - Engine/Converter - add supports for each op benchmarking - refactor optimizer by separating steps - CPU - add supports for Conv3D, Pool3D, ELU, ReverseSequence - fix ArgMax, Permute, Scale, BinaryOp, Slice, SliceTf - OpenCL - add half transform in CPU - add broadcast supports for binary - optimize Conv2D, Reshape, Eltwise, Gemm, etc. - OpenGL - add sub, real div supports for binary - add supports for unary - optimize Conv2D, Reshape - Vulkan - add max supports for eltwise - Metal - fix metallib missing problem - Train/Quantization - use express to refactor training codes
2019-09-26 21:02:07 +08:00
extern void ___CPUEluCreator__OpType_ELU__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
extern void ___CPUExpandDimsCreator__OpType_ExpandDims__();
extern void ___CPUFillCreator__OpType_Fill__();
beta 0.2.0.3 - add quantization tool & cpu impl & demo/exec - add thread pool - add tests - fix onnx converter tensor name mismatch - optimize cpu performance with SSE for windows
2019-07-11 13:56:52 +08:00
extern void ___CPUFloatToInt8Creator__OpType_FloatToInt8__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
extern void ___CPUGatherCreator__OpType_Gather__();
- build: - unify schema building in core and converter; - add more build script for android; - add linux build script for python; - ops impl: - add floor mod support in binary; - use eltwise impl in add/max/sub/mul binary for optimization; - remove fake double support in cast; - fix 5d support for concat; - add adjX and adjY support for batch matmul; - optimize conv2d back prop filter; - add pad mode support for conv3d; - fix bug in conv2d & conv depthwise with very small feature map; - optimize binary without broacast; - add data types support for gather; - add gather ND support; - use uint8 data type in gather v2; - add transpose support for matmul; - add matrix band part; - add dim != 4 support for padding, reshape & tensor convert; - add pad type support for pool3d; - make ops based on TensorFlow Lite quantization optional; - add all & any support for reduction; - use type in parameter as output type in reduction; - add int support for unary; - add variable weight support for conv2d; - fix conv2d depthwise weights initialization; - fix type support for transpose; - fix grad outputs count for reduce grad and reshape grad; - fix priorbox & detection output; - fix metal softmax error; - python: - add runSessionWithCallBackInfo interface; - add max nodes limit (1400) for visualization tool; - fix save error in python3; - align default dim; - convert: - add extra design for optimization; - add more post converting optimizers; - add caffe v1 weights blob support; - add cast, unary, conv transpose support for onnx model; - optimize batchnorm, conv with variable weights, prelu, reshape, slice, upsample for onnx model; - add cos/sin/atan/tan support for unary for tensorflow model; - add any/all support for reduction for tensorflow model; - add elu, conv3d, pool3d support for tensorflow model; - optimize argmax, batchnorm, concat, batch to space, conv with variable weights, prelu, slice for tensorflow model; - others: - fix size computer lock; - fix thread pool deadlock; - add express & parameters in express; - rewrite blitter chooser without static map; - add tests for expr;
2019-10-29 13:37:26 +08:00
extern void ___CPUGatherNDCreator__OpType_GatherND__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
extern void ___CPUGatherV2Creator__OpType_GatherV2__();
extern void ___CPUInnerProductCreator__OpType_InnerProduct__();
Update
2019-12-27 22:16:57 +08:00
extern void ___CPUInstanceNormCreator__OpType_InstanceNorm__();
beta 0.2.0.3 - add quantization tool & cpu impl & demo/exec - add thread pool - add tests - fix onnx converter tensor name mismatch - optimize cpu performance with SSE for windows
2019-07-11 13:56:52 +08:00
extern void ___CPUInt8ToFloatCreator__OpType_Int8ToFloat__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
extern void ___CPUInterpCreator__OpType_Interp__();
extern void ___CPULRNCreator__OpType_LRN__();
extern void ___CPULSTMCreator__OpType_LSTM__();
Update
2019-12-27 22:16:57 +08:00
extern void ___CPULinSpaceCreator__OpType_LinSpace__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
extern void ___CPUMatMulCreator__OpType_MatMul__();
- build: - unify schema building in core and converter; - add more build script for android; - add linux build script for python; - ops impl: - add floor mod support in binary; - use eltwise impl in add/max/sub/mul binary for optimization; - remove fake double support in cast; - fix 5d support for concat; - add adjX and adjY support for batch matmul; - optimize conv2d back prop filter; - add pad mode support for conv3d; - fix bug in conv2d & conv depthwise with very small feature map; - optimize binary without broacast; - add data types support for gather; - add gather ND support; - use uint8 data type in gather v2; - add transpose support for matmul; - add matrix band part; - add dim != 4 support for padding, reshape & tensor convert; - add pad type support for pool3d; - make ops based on TensorFlow Lite quantization optional; - add all & any support for reduction; - use type in parameter as output type in reduction; - add int support for unary; - add variable weight support for conv2d; - fix conv2d depthwise weights initialization; - fix type support for transpose; - fix grad outputs count for reduce grad and reshape grad; - fix priorbox & detection output; - fix metal softmax error; - python: - add runSessionWithCallBackInfo interface; - add max nodes limit (1400) for visualization tool; - fix save error in python3; - align default dim; - convert: - add extra design for optimization; - add more post converting optimizers; - add caffe v1 weights blob support; - add cast, unary, conv transpose support for onnx model; - optimize batchnorm, conv with variable weights, prelu, reshape, slice, upsample for onnx model; - add cos/sin/atan/tan support for unary for tensorflow model; - add any/all support for reduction for tensorflow model; - add elu, conv3d, pool3d support for tensorflow model; - optimize argmax, batchnorm, concat, batch to space, conv with variable weights, prelu, slice for tensorflow model; - others: - fix size computer lock; - fix thread pool deadlock; - add express & parameters in express; - rewrite blitter chooser without static map; - add tests for expr;
2019-10-29 13:37:26 +08:00
extern void ___CPUMatrixBandPartCreator__OpType_MatrixBandPart__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
extern void ___CPUMomentsCreator__OpType_Moments__();
extern void ___CPUNonMaxSuppressionV2Creator__OpType_NonMaxSuppressionV2__();
extern void ___CPUNormalizeCreator__OpType_Normalize__();
Update
2019-12-27 22:16:57 +08:00
extern void ___CPUOneHotCreator__OpType_OneHot__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
extern void ___CPUPackCreator__OpType_Pack__();
beta 0.2.0.2 - CPU - add padding support - fix bug in permute when channel % 4 != 0 - fix bug in exp with extreme value - OpenCL - add protecting logics - OpenGL - add protecting logics - support NCHW format in Squeeze and Reshape - Converter - add ShuffleChannel support for Caffe - add Clip/Transpose/Unary/Pad supports for ONNX
2019-07-02 18:01:08 +08:00
extern void ___CPUPaddingCreator__OpType_Padding__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
extern void ___CPUPermuteCreator__OpType_Permute__();
extern void ___CPUPoolCreator__OpType_Pooling__();
- dynamic computation graph (beta) - add supports (/express) - add tests - add benchmarks with it (/benchmark/exprModels) - Python - MNN engine and tools were submitted to pip - available on Windows/macOS/Linux - Engine/Converter - add supports for each op benchmarking - refactor optimizer by separating steps - CPU - add supports for Conv3D, Pool3D, ELU, ReverseSequence - fix ArgMax, Permute, Scale, BinaryOp, Slice, SliceTf - OpenCL - add half transform in CPU - add broadcast supports for binary - optimize Conv2D, Reshape, Eltwise, Gemm, etc. - OpenGL - add sub, real div supports for binary - add supports for unary - optimize Conv2D, Reshape - Vulkan - add max supports for eltwise - Metal - fix metallib missing problem - Train/Quantization - use express to refactor training codes
2019-09-26 21:02:07 +08:00
extern void ___CPUPool3DCreator__OpType_Pooling3D__();
beta 0.2.0.0 - replace FreeImage with stb_image - warn unicode error in Windows compiling - separate clang/gcc build script for android - add default values in fbs - optimize CPU conv / conv depthwise / deconv / deconv depthwise / lstm / sigmoid - add sub support in eltwise - add reciprocal / log1p / log in unary - add zero like / select / set diff 1d - add batch support for permute - add training codes - fix metal error in dynamic separate storage type handling
2019-06-17 20:10:35 +08:00
extern void ___CPUPoolGradCreator__OpType_PoolGrad__();
beta 0.2.0.3 - add quantization tool & cpu impl & demo/exec - add thread pool - add tests - fix onnx converter tensor name mismatch - optimize cpu performance with SSE for windows
2019-07-11 13:56:52 +08:00
extern void ___CPUPoolInt8Creator__OpType_PoolInt8__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
extern void ___CPUPriorBoxCreator__OpType_PriorBox__();
extern void ___CPUProposalCreator__OpType_Proposal__();
extern void ___CPUDepthwiseCreator__OpType_QuantizedDepthwiseConv2D__();
extern void ___CPUQuantizedAddCreator__OpType_QuantizedAdd__();
extern void ___CPUQuantizedAvgPoolCreator__OpType_QuantizedAvgPool__();
extern void ___CPUQuantizedConcatCreator__OpType_QuantizedConcat__();
extern void ___CPUQuantizedLogisticCreator__OpType_QuantizedLogistic__();
extern void ___CPUQuantizedMaxPoolCreator__OpType_QuantizedMaxPool__();
extern void ___CPUQuantizedReshapeCreator__OpType_QuantizedReshape__();
extern void ___CPUQuantizedSoftmaxCreator__OpType_QuantizedSoftmax__();
extern void ___CPURNNSequenceGRUCreator__OpType_RNNSequenceGRU__();
extern void ___CPUROIPoolingCreator__OpType_ROIPooling__();
extern void ___CPURangeCreator__OpType_Range__();
extern void ___CPURankCreator__OpType_Rank__();
extern void ___CPUReduceJoinCreator__OpType_ReduceJoin__();
extern void ___CPUReductionCreator__OpType_Reduction__();
extern void ___CPUReluCreator__OpType_ReLU__();
extern void ___CPUReluCreator__OpType_PReLU__();
extern void ___CPURelu6Creator__OpType_ReLU6__();
beta 0.2.0.0 - replace FreeImage with stb_image - warn unicode error in Windows compiling - separate clang/gcc build script for android - add default values in fbs - optimize CPU conv / conv depthwise / deconv / deconv depthwise / lstm / sigmoid - add sub support in eltwise - add reciprocal / log1p / log in unary - add zero like / select / set diff 1d - add batch support for permute - add training codes - fix metal error in dynamic separate storage type handling
2019-06-17 20:10:35 +08:00
extern void ___CPUReluGradCreator__OpType_ReluGrad__();
extern void ___CPUReluGradCreator__OpType_Relu6Grad__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
extern void ___CPUReshapeCreator__OpType_Reshape__();
extern void ___CPUResizeCreator__OpType_Resize__();
- dynamic computation graph (beta) - add supports (/express) - add tests - add benchmarks with it (/benchmark/exprModels) - Python - MNN engine and tools were submitted to pip - available on Windows/macOS/Linux - Engine/Converter - add supports for each op benchmarking - refactor optimizer by separating steps - CPU - add supports for Conv3D, Pool3D, ELU, ReverseSequence - fix ArgMax, Permute, Scale, BinaryOp, Slice, SliceTf - OpenCL - add half transform in CPU - add broadcast supports for binary - optimize Conv2D, Reshape, Eltwise, Gemm, etc. - OpenGL - add sub, real div supports for binary - add supports for unary - optimize Conv2D, Reshape - Vulkan - add max supports for eltwise - Metal - fix metallib missing problem - Train/Quantization - use express to refactor training codes
2019-09-26 21:02:07 +08:00
extern void ___CPUReverseSequenceCreator__OpType_ReverseSequence__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
extern void ___CPUScaleCreator__OpType_Scale__();
Update
2019-12-27 22:16:57 +08:00
extern void ___CPUScatterNdCreator__OpType_ScatterNd__();
beta 0.2.0.0 - replace FreeImage with stb_image - warn unicode error in Windows compiling - separate clang/gcc build script for android - add default values in fbs - optimize CPU conv / conv depthwise / deconv / deconv depthwise / lstm / sigmoid - add sub support in eltwise - add reciprocal / log1p / log in unary - add zero like / select / set diff 1d - add batch support for permute - add training codes - fix metal error in dynamic separate storage type handling
2019-06-17 20:10:35 +08:00
extern void ___CPUSelectCreator__OpType_Select__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
extern void ___CPUSeluCreator__OpType_Selu__();
beta 0.2.0.0 - replace FreeImage with stb_image - warn unicode error in Windows compiling - separate clang/gcc build script for android - add default values in fbs - optimize CPU conv / conv depthwise / deconv / deconv depthwise / lstm / sigmoid - add sub support in eltwise - add reciprocal / log1p / log in unary - add zero like / select / set diff 1d - add batch support for permute - add training codes - fix metal error in dynamic separate storage type handling
2019-06-17 20:10:35 +08:00
extern void ___CPUSetDiff1DCreator__OpType_SetDiff1D__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
extern void ___CPUShapeCreator__OpType_Shape__();
extern void ___CPUSigmoidCreator__OpType_Sigmoid__();
extern void ___CPUSizeCreator__OpType_Size__();
extern void ___CPUSliceCreator__OpType_Slice__();
extern void ___CPUSliceTfCreator__OpType_SliceTf__();
extern void ___CPUSoftmaxCreator__OpType_Softmax__();
beta 0.2.0.0 - replace FreeImage with stb_image - warn unicode error in Windows compiling - separate clang/gcc build script for android - add default values in fbs - optimize CPU conv / conv depthwise / deconv / deconv depthwise / lstm / sigmoid - add sub support in eltwise - add reciprocal / log1p / log in unary - add zero like / select / set diff 1d - add batch support for permute - add training codes - fix metal error in dynamic separate storage type handling
2019-06-17 20:10:35 +08:00
extern void ___CPUSoftmaxGradCreator__OpType_SoftmaxGrad__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
extern void ___SpaceBatchCreator__OpType_SpaceToBatchND__();
beta 0.2.0.5 - CPU - add support for DepthToSpace & SpaceToDepth ops - OpenGL - add Android demo - add half / float runtime option - add support for ROIPooling, Squeeze - fix bugs in conv im2col - OpenCL - fix Concat, Eltwise, Reshape bugs - Tools - add KL threshold method in quantization tool - support optimization for graph with multiple rnn
2019-07-25 13:36:35 +08:00
extern void ___SpaceToDepthCreator__OpType_SpaceToDepth__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
extern void ___CPUSpatialProductCreator__OpType_SpatialProduct__();
extern void ___CPUSqueezeCreator__OpType_Squeeze__();
beta 0.1.1.5 - cpu & gpu - add ceil mode in pool - fix softmax with neg axis - cpu - add unsqueeze op - optimize lstm - gpu - add 5x5 winograd in metal - add batch support for winograd in opencl - onnx - add concat / gather / shape / squeeze / unsqueeze - fix data type support in constant
2019-06-05 10:45:59 +08:00
extern void ___CPUSqueezeCreator__OpType_Unsqueeze__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
extern void ___CPUStridedSliceCreator__OpType_StridedSlice__();
extern void ___CPUTFQuantizedConv2DCreator__OpType_TfQuantizedConv2D__();
extern void ___CPUTanhCreator__OpType_TanH__();
extern void ___CPUTensorConvertFactory__OpType_ConvertTensor__();
Update
2019-12-27 22:16:57 +08:00
extern void ___CPUThresholdCreator__OpType_Threshold__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
extern void ___CPUTileCreator__OpType_Tile__();
extern void ___CPUTopKV2Creator__OpType_TopKV2__();
extern void ___CPUTransposeeCreator__OpType_Transpose__();
extern void ___CPUUnaryCreator__OpType_UnaryOp__();
extern void ___CPUUnpackCreator__OpType_Unpack__();
Update
2019-12-27 22:16:57 +08:00
extern void ___CPUUnravelIndexCreator__OpType_UnravelIndex__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
extern void ___CPUWhereCreator__OpType_Where__();
beta 0.2.0.0 - replace FreeImage with stb_image - warn unicode error in Windows compiling - separate clang/gcc build script for android - add default values in fbs - optimize CPU conv / conv depthwise / deconv / deconv depthwise / lstm / sigmoid - add sub support in eltwise - add reciprocal / log1p / log in unary - add zero like / select / set diff 1d - add batch support for permute - add training codes - fix metal error in dynamic separate storage type handling
2019-06-17 20:10:35 +08:00
extern void ___CPUZeroLikeCreator__OpType_ZerosLike__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
fix register spell
2019-05-08 16:37:43 +08:00
void registerCPUOps() {
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
___CPUArgMaxCreator__OpType_ArgMax__();
Update
2019-12-27 22:16:57 +08:00
___CPUArgMaxCreator__OpType_ArgMin__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
___CPUAsStringCreator__OpType_AsString__();
___CPUBatchMatMulCreator__OpType_BatchMatMul__();
___CPUBatchToSpaceNDCreator__OpType_BatchToSpaceND__();
___CPUBinaryCreator__OpType_BinaryOp__();
Update
2019-12-27 22:16:57 +08:00
___CPUBroadcastToCreator__OpType_BroadcastTo__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
___CPUCastCreator__OpType_Cast__();
___CPUConcatCreator__OpType_Concat__();
___CPUConstCreator__OpType_Const__();
Update
2019-12-27 22:16:57 +08:00
___CPUConstCreator__OpType_TrainableParam__();
beta 0.2.0.0 - replace FreeImage with stb_image - warn unicode error in Windows compiling - separate clang/gcc build script for android - add default values in fbs - optimize CPU conv / conv depthwise / deconv / deconv depthwise / lstm / sigmoid - add sub support in eltwise - add reciprocal / log1p / log in unary - add zero like / select / set diff 1d - add batch support for permute - add training codes - fix metal error in dynamic separate storage type handling
2019-06-17 20:10:35 +08:00
___CPUConv2DBackPropFilterCreator__OpType_Conv2DBackPropFilter__();
beta 0.2.0.3 - add quantization tool & cpu impl & demo/exec - add thread pool - add tests - fix onnx converter tensor name mismatch - optimize cpu performance with SSE for windows
2019-07-11 13:56:52 +08:00
___CPUConvInt8Creator__OpType_ConvInt8__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
___ConvolutionFactory__OpType_Convolution__();
- dynamic computation graph (beta) - add supports (/express) - add tests - add benchmarks with it (/benchmark/exprModels) - Python - MNN engine and tools were submitted to pip - available on Windows/macOS/Linux - Engine/Converter - add supports for each op benchmarking - refactor optimizer by separating steps - CPU - add supports for Conv3D, Pool3D, ELU, ReverseSequence - fix ArgMax, Permute, Scale, BinaryOp, Slice, SliceTf - OpenCL - add half transform in CPU - add broadcast supports for binary - optimize Conv2D, Reshape, Eltwise, Gemm, etc. - OpenGL - add sub, real div supports for binary - add supports for unary - optimize Conv2D, Reshape - Vulkan - add max supports for eltwise - Metal - fix metallib missing problem - Train/Quantization - use express to refactor training codes
2019-09-26 21:02:07 +08:00
___Convolution3DCreator__OpType_Convolution3D__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
___CPUConvolutionDepthwiseCreator__OpType_ConvolutionDepthwise__();
beta 0.2.0.4 - bug fix for quantization tool - bug fix/performance update for thread pool - bug fix for converters - tutorial/doc update - more op support
2019-07-19 17:09:09 +08:00
___CPUCosineSimilarityCreator__OpType_CosineSimilarity__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
___CPUCropCreator__OpType_Crop__();
___CPUCropAndResizeCreator__OpType_CropAndResize__();
___CPUDeconvolutionCreator__OpType_Deconvolution__();
___CPUDeconvolutionDepthwiseCreator__OpType_DeconvolutionDepthwise__();
beta 0.2.0.5 - CPU - add support for DepthToSpace & SpaceToDepth ops - OpenGL - add Android demo - add half / float runtime option - add support for ROIPooling, Squeeze - fix bugs in conv im2col - OpenCL - fix Concat, Eltwise, Reshape bugs - Tools - add KL threshold method in quantization tool - support optimization for graph with multiple rnn
2019-07-25 13:36:35 +08:00
___DepthToSpaceCreator__OpType_DepthToSpace__();
beta 0.2.0.3 - add quantization tool & cpu impl & demo/exec - add thread pool - add tests - fix onnx converter tensor name mismatch - optimize cpu performance with SSE for windows
2019-07-11 13:56:52 +08:00
___CPUDepthwiseConvInt8Creator__OpType_DepthwiseConvInt8__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
___CPUDequantizeCreator__OpType_Dequantize__();
___CPUDetectionOutputCreator__OpType_DetectionOutput__();
0.2.1.5 # integration - add travis CI - fix building parameters for python # converter - add half storage option for MNN converter - fix op name lost in converter - fix converter bug for print input output, identity remove output # ops - add quantized Convolution & Deconvolution support on OpenCL - add more expression supports - add DetectionPostProcess Op for TensorFlow Lite (ssd is supported directly now) - add supports for LSTM & ELU for ONNX - add support for Convolution that weights is not constant for ONNX - fix Unary Op compile error on Linux - fix Metal backend buffer reuse after resize - fix Metal raw memory access after model releasing - fix redundant transpose in Winograd generater
2019-11-15 14:22:45 +08:00
___CPUDetectionPostProcessCreator__OpType_DetectionPostProcess__();
Update
2019-12-27 22:16:57 +08:00
___CPUDilation2DCreator__OpType_Dilation2D__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
___CPUEltwiesCreator__OpType_Eltwise__();
beta 0.2.0.8 - add NaN check-up - add quantification support for ScaleAdd Op - add binary to eltwise optimization - add console logs for quantization tool - better document for quantization tool - replace redundant dimension flags with dimension format - optimize performance of TensorFlow Lite Quantized Convolution - fix axis support for ONNX softmax - fix get performance compile error on Windows
2019-08-22 20:13:46 +08:00
___CPUEltwiseInt8Creator__OpType_EltwiseInt8__();
- dynamic computation graph (beta) - add supports (/express) - add tests - add benchmarks with it (/benchmark/exprModels) - Python - MNN engine and tools were submitted to pip - available on Windows/macOS/Linux - Engine/Converter - add supports for each op benchmarking - refactor optimizer by separating steps - CPU - add supports for Conv3D, Pool3D, ELU, ReverseSequence - fix ArgMax, Permute, Scale, BinaryOp, Slice, SliceTf - OpenCL - add half transform in CPU - add broadcast supports for binary - optimize Conv2D, Reshape, Eltwise, Gemm, etc. - OpenGL - add sub, real div supports for binary - add supports for unary - optimize Conv2D, Reshape - Vulkan - add max supports for eltwise - Metal - fix metallib missing problem - Train/Quantization - use express to refactor training codes
2019-09-26 21:02:07 +08:00
___CPUEluCreator__OpType_ELU__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
___CPUExpandDimsCreator__OpType_ExpandDims__();
___CPUFillCreator__OpType_Fill__();
beta 0.2.0.3 - add quantization tool & cpu impl & demo/exec - add thread pool - add tests - fix onnx converter tensor name mismatch - optimize cpu performance with SSE for windows
2019-07-11 13:56:52 +08:00
___CPUFloatToInt8Creator__OpType_FloatToInt8__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
___CPUGatherCreator__OpType_Gather__();
- build: - unify schema building in core and converter; - add more build script for android; - add linux build script for python; - ops impl: - add floor mod support in binary; - use eltwise impl in add/max/sub/mul binary for optimization; - remove fake double support in cast; - fix 5d support for concat; - add adjX and adjY support for batch matmul; - optimize conv2d back prop filter; - add pad mode support for conv3d; - fix bug in conv2d & conv depthwise with very small feature map; - optimize binary without broacast; - add data types support for gather; - add gather ND support; - use uint8 data type in gather v2; - add transpose support for matmul; - add matrix band part; - add dim != 4 support for padding, reshape & tensor convert; - add pad type support for pool3d; - make ops based on TensorFlow Lite quantization optional; - add all & any support for reduction; - use type in parameter as output type in reduction; - add int support for unary; - add variable weight support for conv2d; - fix conv2d depthwise weights initialization; - fix type support for transpose; - fix grad outputs count for reduce grad and reshape grad; - fix priorbox & detection output; - fix metal softmax error; - python: - add runSessionWithCallBackInfo interface; - add max nodes limit (1400) for visualization tool; - fix save error in python3; - align default dim; - convert: - add extra design for optimization; - add more post converting optimizers; - add caffe v1 weights blob support; - add cast, unary, conv transpose support for onnx model; - optimize batchnorm, conv with variable weights, prelu, reshape, slice, upsample for onnx model; - add cos/sin/atan/tan support for unary for tensorflow model; - add any/all support for reduction for tensorflow model; - add elu, conv3d, pool3d support for tensorflow model; - optimize argmax, batchnorm, concat, batch to space, conv with variable weights, prelu, slice for tensorflow model; - others: - fix size computer lock; - fix thread pool deadlock; - add express & parameters in express; - rewrite blitter chooser without static map; - add tests for expr;
2019-10-29 13:37:26 +08:00
___CPUGatherNDCreator__OpType_GatherND__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
___CPUGatherV2Creator__OpType_GatherV2__();
___CPUInnerProductCreator__OpType_InnerProduct__();
Update
2019-12-27 22:16:57 +08:00
___CPUInstanceNormCreator__OpType_InstanceNorm__();
beta 0.2.0.3 - add quantization tool & cpu impl & demo/exec - add thread pool - add tests - fix onnx converter tensor name mismatch - optimize cpu performance with SSE for windows
2019-07-11 13:56:52 +08:00
___CPUInt8ToFloatCreator__OpType_Int8ToFloat__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
___CPUInterpCreator__OpType_Interp__();
___CPULRNCreator__OpType_LRN__();
___CPULSTMCreator__OpType_LSTM__();
Update
2019-12-27 22:16:57 +08:00
___CPULinSpaceCreator__OpType_LinSpace__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
___CPUMatMulCreator__OpType_MatMul__();
- build: - unify schema building in core and converter; - add more build script for android; - add linux build script for python; - ops impl: - add floor mod support in binary; - use eltwise impl in add/max/sub/mul binary for optimization; - remove fake double support in cast; - fix 5d support for concat; - add adjX and adjY support for batch matmul; - optimize conv2d back prop filter; - add pad mode support for conv3d; - fix bug in conv2d & conv depthwise with very small feature map; - optimize binary without broacast; - add data types support for gather; - add gather ND support; - use uint8 data type in gather v2; - add transpose support for matmul; - add matrix band part; - add dim != 4 support for padding, reshape & tensor convert; - add pad type support for pool3d; - make ops based on TensorFlow Lite quantization optional; - add all & any support for reduction; - use type in parameter as output type in reduction; - add int support for unary; - add variable weight support for conv2d; - fix conv2d depthwise weights initialization; - fix type support for transpose; - fix grad outputs count for reduce grad and reshape grad; - fix priorbox & detection output; - fix metal softmax error; - python: - add runSessionWithCallBackInfo interface; - add max nodes limit (1400) for visualization tool; - fix save error in python3; - align default dim; - convert: - add extra design for optimization; - add more post converting optimizers; - add caffe v1 weights blob support; - add cast, unary, conv transpose support for onnx model; - optimize batchnorm, conv with variable weights, prelu, reshape, slice, upsample for onnx model; - add cos/sin/atan/tan support for unary for tensorflow model; - add any/all support for reduction for tensorflow model; - add elu, conv3d, pool3d support for tensorflow model; - optimize argmax, batchnorm, concat, batch to space, conv with variable weights, prelu, slice for tensorflow model; - others: - fix size computer lock; - fix thread pool deadlock; - add express & parameters in express; - rewrite blitter chooser without static map; - add tests for expr;
2019-10-29 13:37:26 +08:00
___CPUMatrixBandPartCreator__OpType_MatrixBandPart__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
___CPUMomentsCreator__OpType_Moments__();
___CPUNonMaxSuppressionV2Creator__OpType_NonMaxSuppressionV2__();
___CPUNormalizeCreator__OpType_Normalize__();
Update
2019-12-27 22:16:57 +08:00
___CPUOneHotCreator__OpType_OneHot__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
___CPUPackCreator__OpType_Pack__();
beta 0.2.0.2 - CPU - add padding support - fix bug in permute when channel % 4 != 0 - fix bug in exp with extreme value - OpenCL - add protecting logics - OpenGL - add protecting logics - support NCHW format in Squeeze and Reshape - Converter - add ShuffleChannel support for Caffe - add Clip/Transpose/Unary/Pad supports for ONNX
2019-07-02 18:01:08 +08:00
___CPUPaddingCreator__OpType_Padding__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
___CPUPermuteCreator__OpType_Permute__();
___CPUPoolCreator__OpType_Pooling__();
- dynamic computation graph (beta) - add supports (/express) - add tests - add benchmarks with it (/benchmark/exprModels) - Python - MNN engine and tools were submitted to pip - available on Windows/macOS/Linux - Engine/Converter - add supports for each op benchmarking - refactor optimizer by separating steps - CPU - add supports for Conv3D, Pool3D, ELU, ReverseSequence - fix ArgMax, Permute, Scale, BinaryOp, Slice, SliceTf - OpenCL - add half transform in CPU - add broadcast supports for binary - optimize Conv2D, Reshape, Eltwise, Gemm, etc. - OpenGL - add sub, real div supports for binary - add supports for unary - optimize Conv2D, Reshape - Vulkan - add max supports for eltwise - Metal - fix metallib missing problem - Train/Quantization - use express to refactor training codes
2019-09-26 21:02:07 +08:00
___CPUPool3DCreator__OpType_Pooling3D__();
beta 0.2.0.0 - replace FreeImage with stb_image - warn unicode error in Windows compiling - separate clang/gcc build script for android - add default values in fbs - optimize CPU conv / conv depthwise / deconv / deconv depthwise / lstm / sigmoid - add sub support in eltwise - add reciprocal / log1p / log in unary - add zero like / select / set diff 1d - add batch support for permute - add training codes - fix metal error in dynamic separate storage type handling
2019-06-17 20:10:35 +08:00
___CPUPoolGradCreator__OpType_PoolGrad__();
beta 0.2.0.3 - add quantization tool & cpu impl & demo/exec - add thread pool - add tests - fix onnx converter tensor name mismatch - optimize cpu performance with SSE for windows
2019-07-11 13:56:52 +08:00
___CPUPoolInt8Creator__OpType_PoolInt8__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
___CPUPriorBoxCreator__OpType_PriorBox__();
___CPUProposalCreator__OpType_Proposal__();
___CPUDepthwiseCreator__OpType_QuantizedDepthwiseConv2D__();
___CPUQuantizedAddCreator__OpType_QuantizedAdd__();
___CPUQuantizedAvgPoolCreator__OpType_QuantizedAvgPool__();
___CPUQuantizedConcatCreator__OpType_QuantizedConcat__();
___CPUQuantizedLogisticCreator__OpType_QuantizedLogistic__();
___CPUQuantizedMaxPoolCreator__OpType_QuantizedMaxPool__();
___CPUQuantizedReshapeCreator__OpType_QuantizedReshape__();
___CPUQuantizedSoftmaxCreator__OpType_QuantizedSoftmax__();
___CPURNNSequenceGRUCreator__OpType_RNNSequenceGRU__();
___CPUROIPoolingCreator__OpType_ROIPooling__();
___CPURangeCreator__OpType_Range__();
___CPURankCreator__OpType_Rank__();
___CPUReduceJoinCreator__OpType_ReduceJoin__();
___CPUReductionCreator__OpType_Reduction__();
___CPUReluCreator__OpType_ReLU__();
___CPUReluCreator__OpType_PReLU__();
___CPURelu6Creator__OpType_ReLU6__();
beta 0.2.0.0 - replace FreeImage with stb_image - warn unicode error in Windows compiling - separate clang/gcc build script for android - add default values in fbs - optimize CPU conv / conv depthwise / deconv / deconv depthwise / lstm / sigmoid - add sub support in eltwise - add reciprocal / log1p / log in unary - add zero like / select / set diff 1d - add batch support for permute - add training codes - fix metal error in dynamic separate storage type handling
2019-06-17 20:10:35 +08:00
___CPUReluGradCreator__OpType_ReluGrad__();
___CPUReluGradCreator__OpType_Relu6Grad__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
___CPUReshapeCreator__OpType_Reshape__();
___CPUResizeCreator__OpType_Resize__();
- dynamic computation graph (beta) - add supports (/express) - add tests - add benchmarks with it (/benchmark/exprModels) - Python - MNN engine and tools were submitted to pip - available on Windows/macOS/Linux - Engine/Converter - add supports for each op benchmarking - refactor optimizer by separating steps - CPU - add supports for Conv3D, Pool3D, ELU, ReverseSequence - fix ArgMax, Permute, Scale, BinaryOp, Slice, SliceTf - OpenCL - add half transform in CPU - add broadcast supports for binary - optimize Conv2D, Reshape, Eltwise, Gemm, etc. - OpenGL - add sub, real div supports for binary - add supports for unary - optimize Conv2D, Reshape - Vulkan - add max supports for eltwise - Metal - fix metallib missing problem - Train/Quantization - use express to refactor training codes
2019-09-26 21:02:07 +08:00
___CPUReverseSequenceCreator__OpType_ReverseSequence__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
___CPUScaleCreator__OpType_Scale__();
Update
2019-12-27 22:16:57 +08:00
___CPUScatterNdCreator__OpType_ScatterNd__();
beta 0.2.0.0 - replace FreeImage with stb_image - warn unicode error in Windows compiling - separate clang/gcc build script for android - add default values in fbs - optimize CPU conv / conv depthwise / deconv / deconv depthwise / lstm / sigmoid - add sub support in eltwise - add reciprocal / log1p / log in unary - add zero like / select / set diff 1d - add batch support for permute - add training codes - fix metal error in dynamic separate storage type handling
2019-06-17 20:10:35 +08:00
___CPUSelectCreator__OpType_Select__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
___CPUSeluCreator__OpType_Selu__();
beta 0.2.0.0 - replace FreeImage with stb_image - warn unicode error in Windows compiling - separate clang/gcc build script for android - add default values in fbs - optimize CPU conv / conv depthwise / deconv / deconv depthwise / lstm / sigmoid - add sub support in eltwise - add reciprocal / log1p / log in unary - add zero like / select / set diff 1d - add batch support for permute - add training codes - fix metal error in dynamic separate storage type handling
2019-06-17 20:10:35 +08:00
___CPUSetDiff1DCreator__OpType_SetDiff1D__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
___CPUShapeCreator__OpType_Shape__();
___CPUSigmoidCreator__OpType_Sigmoid__();
___CPUSizeCreator__OpType_Size__();
___CPUSliceCreator__OpType_Slice__();
___CPUSliceTfCreator__OpType_SliceTf__();
___CPUSoftmaxCreator__OpType_Softmax__();
beta 0.2.0.0 - replace FreeImage with stb_image - warn unicode error in Windows compiling - separate clang/gcc build script for android - add default values in fbs - optimize CPU conv / conv depthwise / deconv / deconv depthwise / lstm / sigmoid - add sub support in eltwise - add reciprocal / log1p / log in unary - add zero like / select / set diff 1d - add batch support for permute - add training codes - fix metal error in dynamic separate storage type handling
2019-06-17 20:10:35 +08:00
___CPUSoftmaxGradCreator__OpType_SoftmaxGrad__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
___SpaceBatchCreator__OpType_SpaceToBatchND__();
beta 0.2.0.5 - CPU - add support for DepthToSpace & SpaceToDepth ops - OpenGL - add Android demo - add half / float runtime option - add support for ROIPooling, Squeeze - fix bugs in conv im2col - OpenCL - fix Concat, Eltwise, Reshape bugs - Tools - add KL threshold method in quantization tool - support optimization for graph with multiple rnn
2019-07-25 13:36:35 +08:00
___SpaceToDepthCreator__OpType_SpaceToDepth__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
___CPUSpatialProductCreator__OpType_SpatialProduct__();
___CPUSqueezeCreator__OpType_Squeeze__();
beta 0.1.1.5 - cpu & gpu - add ceil mode in pool - fix softmax with neg axis - cpu - add unsqueeze op - optimize lstm - gpu - add 5x5 winograd in metal - add batch support for winograd in opencl - onnx - add concat / gather / shape / squeeze / unsqueeze - fix data type support in constant
2019-06-05 10:45:59 +08:00
___CPUSqueezeCreator__OpType_Unsqueeze__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
___CPUStridedSliceCreator__OpType_StridedSlice__();
___CPUTFQuantizedConv2DCreator__OpType_TfQuantizedConv2D__();
___CPUTanhCreator__OpType_TanH__();
___CPUTensorConvertFactory__OpType_ConvertTensor__();
Update
2019-12-27 22:16:57 +08:00
___CPUThresholdCreator__OpType_Threshold__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
___CPUTileCreator__OpType_Tile__();
___CPUTopKV2Creator__OpType_TopKV2__();
___CPUTransposeeCreator__OpType_Transpose__();
___CPUUnaryCreator__OpType_UnaryOp__();
___CPUUnpackCreator__OpType_Unpack__();
Update
2019-12-27 22:16:57 +08:00
___CPUUnravelIndexCreator__OpType_UnravelIndex__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
___CPUWhereCreator__OpType_Where__();
beta 0.2.0.0 - replace FreeImage with stb_image - warn unicode error in Windows compiling - separate clang/gcc build script for android - add default values in fbs - optimize CPU conv / conv depthwise / deconv / deconv depthwise / lstm / sigmoid - add sub support in eltwise - add reciprocal / log1p / log in unary - add zero like / select / set diff 1d - add batch support for permute - add training codes - fix metal error in dynamic separate storage type handling
2019-06-17 20:10:35 +08:00
___CPUZeroLikeCreator__OpType_ZerosLike__();
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
}
fix backend/op/sizer register
2019-05-09 19:39:33 +08:00
#endif
beta 0.1.1.1 - use code generate for op/backend/sizer register - add pose demo - fix docs & script - improve cpu softmax performance 80% - improve converter ops fuse
2019-05-08 15:44:57 +08:00
}