2019-04-17 10:49:11 +08:00
|
|
|
//
|
|
|
|
// ConvOpt.h
|
|
|
|
// MNN
|
|
|
|
//
|
|
|
|
// Created by MNN on 2018/07/16.
|
|
|
|
// Copyright © 2018, Alibaba Group Holding Limited
|
|
|
|
//
|
|
|
|
|
|
|
|
#ifndef ConvOpt_h
|
|
|
|
#define ConvOpt_h
|
|
|
|
|
|
|
|
#include <stdint.h>
|
|
|
|
#include <stdio.h>
|
|
|
|
|
|
|
|
#ifdef __cplusplus
|
|
|
|
extern "C" {
|
|
|
|
#endif
|
|
|
|
|
|
|
|
void MNNConvRunForUnitDepthWise(float* dst, const float* src, const float* weight, size_t fw, size_t fh,
|
|
|
|
size_t weight_y_step, size_t dilateX_step, size_t dilateY_step);
|
|
|
|
void MNNConvRunForLineDepthwise(float* dst, const float* src, const float* weight, size_t width, size_t src_w_setup,
|
|
|
|
size_t fw, size_t fh, size_t dilateX_step, size_t dilateY_step, size_t height,
|
|
|
|
size_t srcHStep, size_t dstHStep);
|
|
|
|
|
|
|
|
void MNNDeconvRunForUnitDepthWise(const float* dst, float* src, const float* weight, size_t fw, size_t fh,
|
|
|
|
size_t weight_y_step, size_t dilateX_step, size_t dilateY_step);
|
|
|
|
void MNNDeconvRunForLineDepthwise(const float* dst, float* src, const float* weight, size_t width, size_t src_w_setup,
|
|
|
|
size_t fw, size_t fh, size_t dilateX_step, size_t dilateY_step);
|
|
|
|
|
|
|
|
void MNNMatrixAdd(float* C, const float* A, const float* B, size_t widthC4, size_t cStride, size_t aStride,
|
|
|
|
size_t bStride, size_t height);
|
|
|
|
void MNNMatrixSub(float* C, const float* A, const float* B, size_t widthC4, size_t cStride, size_t aStride,
|
|
|
|
size_t bStride, size_t height);
|
2021-04-08 15:34:23 +08:00
|
|
|
void MNNStrassenMergeCFunction(float* c11, float* c12, float* c21, float* c22, float* xAddr, size_t cStride,
|
|
|
|
size_t eSub, size_t hSub);
|
2019-04-17 10:49:11 +08:00
|
|
|
void MNNMatrixMax(float* C, const float* A, const float* B, size_t widthC4, size_t cStride, size_t aStride,
|
|
|
|
size_t bStride, size_t height);
|
|
|
|
void MNNMatrixProd(float* C, const float* A, const float* B, size_t widthC4, size_t cStride, size_t aStride,
|
|
|
|
size_t bStride, size_t height);
|
|
|
|
|
- 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
|
|
|
void MNNMatrixAddCommon(float* C, const float* A, const float* B, size_t width, size_t cStride, size_t aStride, size_t bStride, size_t height);
|
|
|
|
void MNNMatrixSubCommon(float* C, const float* A, const float* B, size_t width, size_t cStride, size_t aStride, size_t bStride, size_t height);
|
|
|
|
void MNNMatrixMaxCommon(float* C, const float* A, const float* B, size_t width, size_t cStride, size_t aStride, size_t bStride, size_t height);
|
|
|
|
|
|
|
|
void MNNMatrixProdCommon(float* C, const float* A, const float* B, size_t width, size_t cStride, size_t aStride, size_t bStride, size_t height);
|
2020-07-04 01:21:30 +08:00
|
|
|
|
2019-04-17 10:49:11 +08:00
|
|
|
#ifdef __cplusplus
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#endif /* ConvOpt_h */
|