import torch
import torch.nn as nn
from torch import Tensor
from typing import List, Callable
#通道重排
def channel_shuffle(x: Tensor, groups: int) -> Tensor:
batch_size, num_channels,height,width = x.size()
channel_pre_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, channel_pre_group, height, width)
x = torch.transpose(x, 1, 2).contiguous()
#flatten
x = x.view(batch_size, -1, height, width)
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_feature = 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
# 当 stride = 2时就往下走,如果等于2 就判断 input_c == branch_features << 1
assert (self.stride!=1) or(input_c == branch_feature << 1)
#左边的分支
if self.stride ==2 :
self.branch1 = nn.Sequential(
self.depthwise_conv(input_c, input_c, kernel_size=3, stride=self.stride, padding=1),
nn.BatchNorm2d(input_c),
nn.Conv2d(input_c, branch_feature, kernel_size=1, stride=1, padding=0, bias=False),
nn.BatchNorm2d(branch_feature),
nn.ReLU(inplace=True)
)
else:
self.branch1 = nn.Sequential()
self.branch2 = nn.Sequential(
nn.Conv2d(input_c if self.stride>1 else branch_feature, branch_feature, kernel_size=1,
stride=1, padding=0, bias=False),
nn.BatchNorm2d(branch_feature),
nn.ReLU(inplace=True),
self.depthwise_conv(branch_feature, branch_feature, kernel_size=3, stride=self.stride, padding=1),
nn.BatchNorm2d(branch_feature),
nn.Conv2d(branch_feature, branch_feature,kernel_size=1, stride=1, padding=0, bias=False),
nn.BatchNorm2d(branch_feature),
nn.ReLU(inplace=True)
)
@staticmethod
def depthwise_conv(input_c, output_c, kernel_size, stride=1, padding=0, bias=False)->nn.Conv2d:
return nn.Conv2d(in_channels=input_c,
out_channels=output_c,
kernel_size=kernel_size,
stride=stride,
padding=padding,
bias=bias,
groups=input_c)
def forward(self, x: Tensor) -> Tensor:
if self.stride ==1 :
#dim=1 在channel维度上
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
#RGB
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 for mypy
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))
#给self.stage_ 设置值
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):
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]) #avgpool 2,3 是h和w维度
x = self.fc(x)
return x
def forward(self, x: Tensor) -> Tensor:
return self._forward_impl(x)
def shufflenet_v2_x0_5(num_classes = 1000):
#weight: https://download.pytorch.org/models/shufflenetv2_x0.5-f707e7126e.pth
model = ShuffleNetV2(stages_repeats=[4, 8, 4],
stages_out_channels = [24, 48, 96, 192, 1024],
num_classes = num_classes
)
return model
def shufflenet_v2_x1_0(num_classes = 1000):
#weight: https://download.pytorch.org/models/shufflenetv2_x1-5666bf0f80.pth
model = ShuffleNetV2(stages_repeats=[4, 8, 4],
stages_out_channels = [24, 116, 232, 464, 1024],
num_classes = num_classes
)
return model
def shufflenet_v2_x1_5(num_classes = 1000):
#weight: https://download.pytorch.org/models/shufflenetv2_x1_5-3c479a10.pth
model = ShuffleNetV2(stages_repeats=[4, 8, 4],
stages_out_channels = [24, 176, 352, 704, 1024],
num_classes = num_classes
)
return model
def shufflenet_v2_x2_0(num_classes = 1000):
#weight: https://download.pytorch.org/models/shufflenetv2_x2_0-8be3c8ee.pth
model = ShuffleNetV2(stages_repeats=[4, 8, 4],
stages_out_channels = [24, 244, 488, 976, 2048],
num_classes = num_classes
)
return model
10-10
2744
![](https://csdnimg.cn/release/blogv2/dist/pc/img/readCountWhite.png)
“相关推荐”对你有帮助么?
-
非常没帮助
-
没帮助
-
一般
-
有帮助
-
非常有帮助
提交