ResNet50跑CIFAR-100和ImageNet是不同的,对于CIFAR,第一个卷积stride设置为1,是3×3卷积,不降尺寸。跟在后面不是池化层,舍弃了。100类。
class ResNet(nn.Module):
def __init__(self, block, num_block, num_classes=100):
super().__init__()
self.in_channels = 64
self.conv1 = nn.Sequential(
nn.Conv2d(3, 64, kernel_size=3, padding=1,stride = 1, bias=False),
nn.BatchNorm2d(64),
nn.ReLU(inplace=True))
#we use a different inputsize than the original paper
#so conv2_x's stride is 1
self.conv2_x = self._make_layer(block, 64, 56, num_block[0], 1)
self.conv3_x = self._make_layer(block, 128, 28, num_block[1], 2)
self.conv4_x = self._make_layer(block, 256, 14, num_block[2], 2)
self.conv5_x = self._make_layer(block, 512, 7, num_block[3], 2)
self.avg_pool = nn.AdaptiveAvgPool2d((1, 1))
self.fc = nn.Linear(512 * block.expansion, num_classes)
def _make_layer(self, block, out_channels, size, num_blocks, stride):
"""make resnet layers(by layer i didnt mean this 'layer' was the
same as a neuron netowork layer, ex. conv layer), one layer may
contain more than one residual block
Args:
block: block type, basic block or bottle neck block
out_channels: output depth channel number of this layer
num_blocks: how many blocks per layer
stride: the stride of the first block of this layer
Return:
return a resnet layer
"""
# we have num_block blocks per layer, the first block
# could be 1 or 2, other blocks would always be 1
strides = [stride] + [1] * (num_blocks - 1)
layers = []
for stride in strides:
layers.append(block(self.in_channels, out_channels, size, stride))
self.in_channels = out_channels * block.expansion
return nn.Sequential(*layers)
def forward(self, x):
output = self.conv1(x)
output = self.conv2_x(output)
output = self.conv3_x(output)
output = self.conv4_x(output)
output = self.conv5_x(output)
output = self.avg_pool(output)
output = output.view(output.size(0), -1)
output = self.fc(output)
return output
而用于224的ImageNet,第一个卷积stride设置为2,是7×7卷积,降尺寸。跟在后面是池化层。1000类。
class ResNet(nn.Module):
def __init__(self, block, num_block, num_classes=1000):
super().__init__()
self.in_channels = 64
self.conv1 = nn.Sequential(
nn.Conv2d(3, 64, kernel_size=7, padding=3,stride = 2, bias=False),
nn.BatchNorm2d(64),
nn.ReLU(inplace=True))
#we use a different inputsize than the original paper
#so conv2_x's stride is 1
self.maxpool=nn.MaxPool2d(kernel_size=3,stride=2,padding=1)
self.conv2_x = self._make_layer(block, 64, 56, num_block[0], 1)
self.conv3_x = self._make_layer(block, 128, 28, num_block[1], 2)
self.conv4_x = self._make_layer(block, 256, 14, num_block[2], 2)
self.conv5_x = self._make_layer(block, 512, 7, num_block[3], 2)
self.avg_pool = nn.AdaptiveAvgPool2d((1, 1))
self.fc = nn.Linear(512 * block.expansion, num_classes)
def _make_layer(self, block, out_channels, size, num_blocks, stride):
"""make resnet layers(by layer i didnt mean this 'layer' was the
same as a neuron netowork layer, ex. conv layer), one layer may
contain more than one residual block
Args:
block: block type, basic block or bottle neck block
out_channels: output depth channel number of this layer
num_blocks: how many blocks per layer
stride: the stride of the first block of this layer
Return:
return a resnet layer
"""
# we have num_block blocks per layer, the first block
# could be 1 or 2, other blocks would always be 1
strides = [stride] + [1] * (num_blocks - 1)
layers = []
for stride in strides:
layers.append(block(self.in_channels, out_channels, size, stride))
self.in_channels = out_channels * block.expansion
return nn.Sequential(*layers)
def forward(self, x):
output = self.conv1(x)
output = self.maxpool(output)
output = self.conv2_x(output)
output = self.conv3_x(output)
output = self.conv4_x(output)
output = self.conv5_x(output)
output = self.avg_pool(output)
output = output.view(output.size(0), -1)
output = self.fc(output)
return output