- 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
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								//
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								//  ShapeConvolution3D.cpp
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								//  MNN
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								//
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								//  Created by MNN on 2019/01/10.
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								//  Copyright © 2018, Alibaba Group Holding Limited
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								//
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								#include <math.h>
							 | 
						
					
						
							
								
									
										
										
										
											2020-11-05 16:41:56 +08:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								#include "shape/SizeComputer.hpp"
							 | 
						
					
						
							
								
									
										
										
										
											2019-12-27 22:16:57 +08:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								#include "core/Macro.h"
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								#include "core/TensorUtils.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 Convolution3DSizeComputer : public SizeComputer {
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								public:
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    virtual bool onComputeSize(const MNN::Op* op, const std::vector<Tensor*>& inputs,
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								                               const std::vector<Tensor*>& outputs) const override {
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        MNN_ASSERT(1 == inputs.size());
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        MNN_ASSERT(1 == outputs.size());
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        auto layer        = op->main_as_Convolution3D()->common();
							 | 
						
					
						
							
								
									
										
											 
										 
										
											
												- 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
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								        auto input = inputs[0];
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        if (input->buffer().dimensions != 5) {
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            return false;
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        }
							 | 
						
					
						
							
								
									
										
										
											
												- 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
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        auto& outputBuffer         = outputs[0]->buffer();
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        outputBuffer.dimensions    = input->buffer().dimensions;
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        outputBuffer.dim[0].extent = input->buffer().dim[0].extent;
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        outputBuffer.dim[1].extent = layer->outputCount();
							 | 
						
					
						
							
								
									
										
											 
										 
										
											
												- 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
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								        
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        for (int i = 0; i < 3; ++i) {
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            const int inputLength = input->length(i + 2), stride = (*layer->strides())[i];
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            if (inputLength <= 0) {
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								                return false;
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            }
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            int outputLength;
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            if (layer->padMode() == PadMode_SAME) {
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								                outputLength = UP_DIV(inputLength, stride);
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            } else {
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								                const int pad = (*layer->pads())[i], kernel = (*layer->kernels())[i], dialate = (*layer->dilates())[i];
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								                const int dialatedKernel = (kernel - 1) * dialate + 1;
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								                outputLength = (inputLength + 2 * pad - dialatedKernel) / stride + 1;
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            }
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            outputBuffer.dim[i + 2].extent = outputLength;
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        }
							 | 
						
					
						
							
								
									
										
										
											
												- 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
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        outputBuffer.type = input->getType();
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        TensorUtils::getDescribe(outputs[0])->dimensionFormat = TensorUtils::getDescribe(inputs[0])->dimensionFormat;
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        return true;
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    }
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								};
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								REGISTER_SHAPE(Convolution3DSizeComputer, OpType_Convolution3D);
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								} // namespace MNN
							 |