MNN/source/backend/cpu/CPUTensorConvert.hpp

41 lines
1.1 KiB
C++
Raw Normal View History

2019-04-17 10:49:11 +08:00
//
// CPUTensorConvert.hpp
// MNN
//
// Created by MNN on 2018/08/04.
// Copyright © 2018, Alibaba Group Holding Limited
//
#ifndef CPUTensorConvert_hpp
#define CPUTensorConvert_hpp
#include "Execution.hpp"
#include "Tensor_generated.h"
namespace MNN {
class CPUTensorConverter : public Execution {
public:
CPUTensorConverter(Backend* b, MNN_DATA_FORMAT source, MNN_DATA_FORMAT dest) : Execution(b) {
mSource = source;
mDest = dest;
}
virtual ~CPUTensorConverter() = default;
- 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
static void NHWC2NC4HW4(const float* source, float* dest, int b, int c, int area);
static void NC4HW42NHWC(const float* dest, float* source, int b, int c, int area);
static void NHWC2NCHW(const float* dest, float* source, int b, int c, int area);
static void NCHW2NHWC(const float* source, float* dest, int b, int c, int area);
2019-04-17 10:49:11 +08:00
static ErrorCode convert(const Tensor* input, const Tensor* output);
virtual ErrorCode onExecute(const std::vector<Tensor*>& inputs, const std::vector<Tensor*>& outputs) override;
private:
MNN_DATA_FORMAT mSource;
MNN_DATA_FORMAT mDest;
};
} // namespace MNN
#endif /* CPUTensorConvert_hpp */