在上一篇 Pytorch实例----CAFAR10数据集分类(ResNet)的识别统计,本篇主要调整Net()类,设计ShuffleNet轻量级网络(+BN),实现对CAFAR10数据集的分类任务。
ShuffleNet网络结构编程实现:
#define shuffle block
class ShuffleBlock(nn.Module):
def __init__(self, groups):
super(ShuffleBlock, self).__init__()
self.groups = groups
def forward(self, x):
'''Channel shuffle: [N,C,H,W] -> [N,g,C/g,H,W] -> [N,C/g,g,H,w] -> [N,C,H,W]'''
N,C,H,W = x.size()
g = self.groups
#use contiguous to make the memory continuous, then use the view function
return x.view(N,g,int(C/g),H,W).permute(0,2,1,3,4).contiguous().view(N,C,H,W)
class Bottleneck(nn.Module):
def __init__(self, in_planes, out_planes, stride, groups):
super(Bottleneck, self).__init__()
self.stride = stride
#channel = channel / 4
mid_planes = int(out_planes/4)
g = 1 if in_planes==24 else groups
#use point wise group conv if channel == 24
self.conv1 = nn.Conv2d(in_planes, mid_planes, kernel_size=1, groups=g, bias=False)
self.bn1 = nn.BatchNorm2d(mid_planes)
self.shuffle1 = ShuffleBlock(groups=g)
self.conv2 = nn.Conv2d(mid_planes, mid_planes,kernel_size=3, stride=stride, padding=1,groups=mid_planes, bias=False)
self.bn2 = nn.BatchNorm2d(mid_planes)
self.conv3 = nn.Conv2d(mid_planes, out_planes,kernel_size=1, groups=groups, bias=False)
self.bn3 = nn.BatchNorm2d(out_planes)
self.shortcut = nn.Sequential()
if stride == 2:
self.shortcut = nn.Sequential(nn.AvgPool2d(3, stride=2, padding=1))
def forward(self, x):
out = F.relu(self.bn1(self.conv1(x)))
out = self.shuffle1(out)
out = F.relu(self.bn2(self.conv2(out)))
out = self.bn3(self.conv3(out))
res = self.shortcut(x)
out = F.relu(torch.cat([out,res], 1)) if self.stride==2 else F.relu(out+res)
return out
class ShuffleNet(nn.Module):
def __init__(self, cfg):
super(ShuffleNet, self).__init__()
out_planes = cfg['out_planes']
num_blocks = cfg['num_blocks']
groups = cfg['groups']
self.conv1 = nn.Conv2d(3, 24, kernel_size=1, bias=False)
self.bn1 = nn.BatchNorm2d(24)
self.in_planes = 24
self.layer1 = self._make_layer(out_planes[0], num_blocks[0], groups)
self.layer2 = self._make_layer(out_planes[1], num_blocks[1], groups)
self.layer3 = self._make_layer(out_planes[2], num_blocks[2], groups)
self.linear = nn.Linear(out_planes[2], 10)
def _make_layer(self, out_planes, num_blocks, groups):
layers = []
for i in range(num_blocks):
if i == 0:
layers.append(Bottleneck(self.in_planes,out_planes-self.in_planes,stride=2, groups=groups))
else:
layers.append(Bottleneck(self.in_planes, out_planes, stride=1, groups=groups))
self.in_planes = out_planes
return nn.Sequential(*layers)
def forward(self, x):
out = F.relu(self.bn1(self.conv1(x)))
out = self.layer1(out)
out = self.layer2(out)
out = self.layer3(out)
out = F.avg_pool2d(out, 4)
out = out.view(out.size(0), -1)
out = self.linear(out)
return out
def ShuffleNetG2():
cfg = {
'out_planes': [200,400,800],
'num_blocks': [4,8,4],
'groups': 2
}
return ShuffleNet(cfg)
def ShuffleNetG3():
cfg = {
'out_planes': [240,480,960],
'num_blocks': [4,8,4],
'groups': 3
}
return ShuffleNet(cfg)
#net = ShuffleNetG3()
整体代码(同前,略)
实验结果:
实验讨论了EPOCH=16和EPOCH=32的训练结果,统计如下:
EPOCH | Loss | Accuracy |
16 | 0.424 | 78% |
32 | 0.151 | 80% |
practice makes perfect !
github source code : https://github.com/GinkgoX/CAFAR10_Classification_Task/blob/master/CAFAR10_ShuffleNet.ipynb