- 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
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								//
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								//  ConvolutionWinograd3D.hpp
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								//  MNN
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								//
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								//  Created by MNN on 2018/09/23.
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								//  Copyright © 2018, Alibaba Group Holding Limited
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								//
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								#ifndef ConvolutionWinograd3d_hpp
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								#define ConvolutionWinograd3d_hpp
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							
								
									
										
										
										
											2019-12-27 22:16:57 +08:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								#include "backend/cpu/CPUConvolution3D.hpp"
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								#include "backend/cpu/compute/WinogradOptFunction.hpp"
							 | 
						
					
						
							
								
									
										
										
											
												- 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
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								namespace MNN {
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								class ConvolutionWinograd3D : public Execution {
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								public:
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    ConvolutionWinograd3D(const Convolution3DCommon *convOp, const Tensor *input, const Tensor *output, Backend *b,
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								                        const float *originWeight, size_t originWeightSize, const float *bias, size_t biasSize,
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								                        int unit);
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    virtual ~ConvolutionWinograd3D();
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    virtual ErrorCode onExecute(const std::vector<Tensor *> &inputs, const std::vector<Tensor *> &outputs) override;
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    virtual ErrorCode onResize(const std::vector<Tensor *> &inputs, const std::vector<Tensor *> &outputs) override;
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    static bool canUseWinograd(const Convolution3DCommon *convOp);
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    static int bestWinogradUnit(const Convolution3DCommon *convOp, const Tensor *input, const Tensor *output,
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								                                int threadnumber);
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								private:
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    int mUnit;
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    int mAlpha;
							 | 
						
					
						
							
								
									
										
											 
										 
										
											
												- 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
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								    PadMode mPadMode;
							 | 
						
					
						
							
								
									
										
										
											
												- 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
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    std::vector<int> mKernels;
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    std::vector<int> mPads;
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    CPUConvolution3D::POSTFUNCTION mPostFunction;
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    std::shared_ptr<Tensor> mWeight;
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    std::shared_ptr<Tensor> mBias;
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    std::shared_ptr<Tensor> mSourceBuffer;
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    std::shared_ptr<Tensor> mDestBuffer;
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    std::shared_ptr<Tensor> mTempBuffer;
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    WinogradFunction::TransformFunc mSourceTransform;
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    WinogradFunction::TransformFunc mDestTransform;
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								};
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								} // namespace MNN
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								#endif /* ConvolutionWinograd3d_hpp */
							 |