ShuffleNet系列 网络结构

论文：ShuffleNet:
ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
论文：ShuffleNet V2:
ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design

ShuffleNet V1

Channel Shuffle：通道打散

SuffleNet Unit

Model Architecture

实验结果

ShuffleNet V2

• 计算速度，5 个轻量级网络要领

Guideline 1

• 卷积输入和输出是相同的通道数时，将最小化内存访问成本，每秒处理图片最多
  

Guideline 2

• 过多的分组卷积会加大内存访问成本，导致训练速度下降，时间上升，但是参数量更低，准确率更高。
  

Guideline 3

• 碎片操作减少网络的并行度，碎片操作：将大的卷积分成小卷积操作进行。
  

Guideline 4

• 不要忽略元素级操作，元素级指的是 Relu，TensorAdd，BiasAdd等等的矩阵元素操作，可以推测这些操作基本没有被算到 FLOPs 中，但是对内存访问成本（MAC）的影响比较大。
  
  

模型结构

代码

from typing import List, Callable

import torch
from torch import Tensor
import torch.nn as nn
 
def channel_shuffle(x: Tensor, groups: int):

    batch_size, num_channels, height, width = x.size()
    channels_per_group = num_channels // groups

    # reshape
    # [batch_size, num_channels, height, width] -> [batch_size, groups, channels_per_group, height, width]
    x = x.view(batch_size, groups, channels_per_group, height, width)

    x = torch.transpose(x, 1, 2).contiguous()

    # flatten
    x = x.view(batch_size, -1, height, width)

    return x 

class InvertedResidual(nn.Module):
    def __init__(self, input_c: int, output_c: int, stride: int):
        super(InvertedResidual, self).__init__()

        if stride not in [1, 2]:
            raise ValueError("illegal stride value.")
        self.stride = stride

        assert output_c % 2 == 0
        branch_features = output_c // 2
        # 当stride为1时，input_channel应该是branch_features的两倍
        # python中 '<<' 是位运算，可理解为计算×2的快速方法
        assert (self.stride != 1) or (input_c == branch_features << 1)

        if self.stride == 2:
            self.branch1 = nn.Sequential(
                self.depthwise_conv(input_c, input_c, kernel_s=3, stride=self.stride, padding=1),
                nn.BatchNorm2d(input_c),
                nn.Conv2d(input_c, branch_features, kernel_size=1, stride=1, padding=0, bias=False),
                nn.BatchNorm2d(branch_features),
                nn.ReLU(inplace=True)
            )
        else:
            self.branch1 = nn.Sequential()

        self.branch2 = nn.Sequential(
            nn.Conv2d(input_c if self.stride > 1 else branch_features, branch_features, kernel_size=1,
                      stride=1, padding=0, bias=False),
            nn.BatchNorm2d(branch_features),
            nn.ReLU(inplace=True),
            self.depthwise_conv(branch_features, branch_features, kernel_s=3, stride=self.stride, padding=1),
            nn.BatchNorm2d(branch_features),
            nn.Conv2d(branch_features, branch_features, kernel_size=1, stride=1, padding=0, bias=False),
            nn.BatchNorm2d(branch_features),
            nn.ReLU(inplace=True)
        )

    @staticmethod
    def depthwise_conv(input_c: int,output_c: int,kernel_s: int,stride: int = 1, padding: int = 0,bias: bool = False):
        return nn.Conv2d(in_channels=input_c, out_channels=output_c, kernel_size=kernel_s,
                         stride=stride, padding=padding, bias=bias, groups=input_c)

    def forward(self, x: Tensor):
        if self.stride == 1:
            x1, x2 = x.chunk(2, dim=1)
            out = torch.cat((x1, self.branch2(x2)), dim=1)
        else:
            out = torch.cat((self.branch1(x), self.branch2(x)), dim=1)
        out = channel_shuffle(out, 2)

        return out


class ShuffleNetV2(nn.Module):
    def __init__(self, stages_repeats: List[int],stages_out_channels: List[int],num_classes: int = 1000,
                 inverted_residual: Callable[..., nn.Module] = InvertedResidual):
        super(ShuffleNetV2, self).__init__()

        if len(stages_repeats) != 3:
            raise ValueError("expected stages_repeats as list of 3 positive ints")
        if len(stages_out_channels) != 5:
            raise ValueError("expected stages_out_channels as list of 5 positive ints")
        self._stage_out_channels = stages_out_channels

        # input RGB image
        input_channels = 3
        output_channels = self._stage_out_channels[0]

        self.conv1 = nn.Sequential(
            nn.Conv2d(input_channels, output_channels, kernel_size=3, stride=2, padding=1, bias=False),
            nn.BatchNorm2d(output_channels),
            nn.ReLU(inplace=True)
        )
        input_channels = output_channels

        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)

        # Static annotations 
        self.stage2: nn.Sequential
        self.stage3: nn.Sequential
        self.stage4: nn.Sequential

        stage_names = ["stage{}".format(i) for i in [2, 3, 4]]
        for name, repeats, output_channels in zip(stage_names, stages_repeats, self._stage_out_channels[1:]):
            seq = [inverted_residual(input_channels, output_channels, 2)]
            for i in range(repeats - 1):
                seq.append(inverted_residual(output_channels, output_channels, 1))
            setattr(self, name, nn.Sequential(*seq))
            input_channels = output_channels

        output_channels = self._stage_out_channels[-1]
        self.conv5 = nn.Sequential(
            nn.Conv2d(input_channels, output_channels, kernel_size=1, stride=1, padding=0, bias=False),
            nn.BatchNorm2d(output_channels),
            nn.ReLU(inplace=True)
        )
        self.fc = nn.Linear(output_channels, num_classes)

    def _forward_impl(self, x: Tensor):
        # See note [TorchScript super()]
        x = self.conv1(x)
        x = self.maxpool(x)
        x = self.stage2(x)
        x = self.stage3(x)
        x = self.stage4(x)
        x = self.conv5(x)
        x = x.mean([2, 3])  # global pool
        x = self.fc(x)
        return x

    def forward(self, x: Tensor):
        return self._forward_impl(x)


"""
Constructs a ShuffleNetV2 with 1.0x output channels, as described in
`"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design"
<https://arxiv.org/abs/1807.11164>`.
weight: https://download.pytorch.org/models/shufflenetv2_x1-5666bf0f80.pth

:param num_classes:
:return:
"""
def shufflenet_v2_x1_0(num_classes=1000):

    model = ShuffleNetV2(stages_repeats=[4, 8, 4],
                         stages_out_channels=[24, 116, 232, 464, 1024],
                         num_classes=num_classes)

    return model

"""
Constructs a ShuffleNetV2 with 0.5x output channels, as described in
`"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design"
<https://arxiv.org/abs/1807.11164>`.
weight: https://download.pytorch.org/models/shufflenetv2_x0.5-f707e7126e.pth

:param num_classes:
:return:
"""
def shufflenet_v2_x0_5(num_classes=1000):

    model = ShuffleNetV2(stages_repeats=[4, 8, 4],
                         stages_out_channels=[24, 48, 96, 192, 1024],
                         num_classes=num_classes)

    return model