ResNet Pytorch实现
ResNet通过引入跨连接层解决了梯度回传消失的问题
如下图所示:
这就是普通的网络连接跟跨层残差连接的对比图,使用普通的连接,上层的梯度必须要一层一层的传回来,而使用残差链接,相当于中间有了一条更短的路,梯度能够从这条更短的路传回来,这避免了梯度过小的情况。
残差网络的结构就是上面这种残差快的堆叠,residual block实现如下:
class residual_block(nn.Module):
def __init__(self, in_channel, out_channel, same_shape=True):
super(residual_block, self).__init__()
self.same_shape = same_shape
stride = 1 if self.same_shape else 2
self.conv1 = conv3x3(in_channel, out_channel, stride=stride)
self.bn1 = nn.BatchNorm2d(out_channel)
self.conv2 = conv3x3(out_channel, out_channel)
self.bn2 = nn.BatchNorm2d(out_channel)
if not self.same_shape:
self.conv3 = nn.Conv2d(in_channel, out_channel, 1, stride=stride)
def forward(self, x):
out = self.conv1(x)
out = F.relu(self.bn1(out), True)
out = self.conv2(out)
out = F.relu(self.bn2(out), True)
if not self.same_shape:
x = self.conv3(x)
return F.relu(x + out, True)
整个ResNet就是residual block模块的堆叠,代码如下:
class resnet(nn.Module):
def __init__(self, in_channel, num_classes, verbose=False):
super(resnet, self).__init__()
self.verbose = verbose
self.block1 = nn.Conv2d(in_channel, 64, 7, 2)
self.block2 = nn.Sequential(
nn.MaxPool2d(3, 2),
residual_block(64, 64),
residual_block(64, 64)
)
self.block3 = nn.Sequential(
residual_block(64, 128, False),
residual_block(128, 128)
)
self.block4 = nn.Sequential(
residual_block(128, 256, False),
residual_block(256, 256)
)
self.block5 = nn.Sequential(
residual_block(256, 512, False),
residual_block(512, 512),
nn.AvgPool2d(3)
)
self.classifier = nn.Linear(512, num_classes)
def forward(self, x):
x = self.block1(x)
if self.verbose:
print('block 1 output: {}'.format(x.shape))
x = self.block2(x)
if self.verbose:
print('block 2 output: {}'.format(x.shape))
x = self.block3(x)
if self.verbose:
print('block 3 output: {}'.format(x.shape))
x = self.block4(x)
if self.verbose:
print('block 4 output: {}'.format(x.shape))
x = self.block5(x)
if self.verbose:
print('block 5 output: {}'.format(x.shape))
x = x.view(x.shape[0], -1)
x = self.classifier(x)
return x