具体理论就不说了。直接看网络结构以及其代码就好。深度学习超级新兵一个，记录下自己的学习过程，有错误欢迎大佬指出。万分感谢！！！！！！！！！！
1.先上网络整体结构。
如下图 分别放出来resnet18 resnet134 resnet50 resnet101 resnet152.文字注释应该写明白了大致的网络结构。
图1
2.对图1中的[ ]进一步说明
图2
图2左侧对应的代码中的BasicBlock， 具体实现一会贴代码。图2的右侧对应代码中的Bottleneck。
3. resnet网络的核心：Shortcut Connection
图3
图3可见两种连接方式：
自己层（cvnv2_x之类）内各个卷积层的连接方式，用实线。对应代码中的
out += identity #构成F(x) + x这个公式
cvnv2_x与conv3_x等层之间的卷积连接方式，用虚线。用虚线连接后可见 两组数据的channels是不同的 这样没法加啊。那么就对 identity的通道数做一次修改。代码中用的downsample来实现。对应代码中的。downsample具体实现可具体查代码
if self.downsample is not None:
identity = self.downsample(x)
out += identity #构成F(x) + x这个公式
4.有了这几步的解释。一个完整的resnet的网络结构以及代码结构就清晰了。说白了就是很深的卷积层加上了个Shortcut Connection连接方式。这样让网络表达能力更好。具体为啥好去看原理吧。
5.贴代码：代码直接在github上下载的，可以自己去下载看，官方代码。代码中几个重要位置都注释了。
#encoding=utf-8
import torch
import torch.nn as nn
__all__ = ['ResNet', 'resnet18', 'resnet34', 'resnet50', 'resnet101',
'resnet152', 'resnext50_32x4d', 'resnext101_32x8d',
'wide_resnet50_2', 'wide_resnet101_2']
model_urls = {
'resnet18': 'https://download.pytorch.org/models/resnet18-5c106cde.pth',
'resnet34': 'https://download.pytorch.org/models/resnet34-333f7ec4.pth',
'resnet50': 'https://download.pytorch.org/models/resnet50-19c8e357.pth',
'resnet101': 'https://download.pytorch.org/models/resnet101-5d3b4d8f.pth',
'resnet152': 'https://download.pytorch.org/models/resnet152-b121ed2d.pth',
'resnext50_32x4d': 'https://download.pytorch.org/models/resnext50_32x4d-7cdf4587.pth',
'resnext101_32x8d': 'https://download.pytorch.org/models/resnext101_32x8d-8ba56ff5.pth',
'wide_resnet50_2': 'https://download.pytorch.org/models/wide_resnet50_2-95faca4d.pth',
'wide_resnet101_2': 'https://download.pytorch.org/models/wide_resnet101_2-32ee1156.pth',
}
def conv3x3(in_planes, out_planes, stride=1, groups=1, dilation=1):
"""3x3 convolution with padding"""
return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
padding=dilation, groups=groups, bias=False, dilation=dilation)
def conv1x1(in_planes, out_planes, stride=1):
"""1x1 convolution"""
return nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=stride, bias=False)
class BasicBlock(nn.Module):#一个BasicBlock对应于图1中的【】 【】后面乘几 就是说这种BasicBlock调用几次
expansion = 1
def __init__(self, inplanes, planes, stride=1, downsample=None, groups=1,
base_width=64, dilation=1, norm_layer=None):
super(BasicBlock, self).__init__()
if norm_layer is None:
norm_layer = nn.BatchNorm2d
if groups != 1 or base_width != 64:
raise ValueError('BasicBlock only supports groups=1 and base_width=64')
if dilation > 1:
raise NotImplementedError("Dilation > 1 not supported in BasicBlock")
# Both self.conv1 and self.downsample layers downsample the input when stride != 1
self.conv1 = conv3x3(inplanes, planes, stride)
self.bn1 = norm_layer(planes)
self.relu = nn.ReLU(inplace=True)
self.conv2 = conv3x3(planes, planes)
self.bn2 = norm_layer(planes)
self.downsample = downsample
self.stride = stride
def forward(self, x):
identity = x #x 给自己先备份一份
out = self.conv1(x)#对x做卷积
out = self.bn1(out)#对x归一化
out = self.relu(out)#对x用激活函数
out = self.conv2(out)#对x做卷积
out = self.bn2(out)#归一化
if self.downsample is not None:
identity = self.downsample(x)
out += identity #这个是 对应图2中的弯曲的箭头连接
out = self.relu(out)
#上面这些对应图1中的【】中括号里面的操作
return out
class Bottleneck(nn.Module):
# Bottleneck in torchvision places the stride for downsampling at 3x3 convolution(self.conv2)
# while original implementation places the stride at the first 1x1 convolution(self.conv1)
# according to "Deep residual learning for image recognition"https://arxiv.org/abs/1512.03385.
# This variant is also known as ResNet V1.5 and improves accuracy according to
# https://ngc.nvidia.com/catalog/model-scripts/nvidia:resnet_50_v1_5_for_pytorch.
expansion = 4
def __init__(self, inplanes, planes, stride=1, downsample=None, groups=1,
base_width=64, dilation=1, norm_layer=None):
super(Bottleneck, self).__init__()
if norm_layer is None:
norm_layer = nn.BatchNorm2d
width = int(planes * (base_width / 64.)) * groups
# Both self.conv2 and self.downsample layers downsample the input when stride != 1
self.conv1 = conv1x1(inplanes, width)
self.bn1 = norm_layer(width)
self.conv2 = conv3x3(width, width, stride, groups, dilation)
self.bn2 = norm_layer(width)
self.conv3 = conv1x1(width, planes * self.expansion)
self.bn3 = norm_layer(planes * self.expansion)
self.relu = nn.ReLU(inplace=True)
self.downsample = downsample
self.stride = stride
def forward(self, x):
identity = x
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
out = self.relu(out)
out = self.conv3(out)
out = self.bn3(out)
if self.downsample is not None:
identity = self.downsample(x)
out += identity
out = self.relu(out)
return out
class ResNet(nn.Module):
def __init__(self, block, layers, num_classes=6, zero_init_residual=False,
groups=1, width_per_group=64, replace_stride_with_dilation=None,
norm_layer=None):
super(ResNet, self).__init__()
if norm_layer is None:
norm_layer = nn.BatchNorm2d
self._norm_layer = norm_layer
self.inplanes = 64
self.dilation = 1
if replace_stride_with_dilation is None:
# each element in the tuple indicates if we should replace
# the 2x2 stride with a dilated convolution instead
replace_stride_with_dilation = [False, False, False]
if len(replace_stride_with_dilation) != 3:
raise ValueError("replace_stride_with_dilation should be None "
"or a 3-element tuple, got {}".format(replace_stride_with_dilation))
self.groups = groups
self.base_width = width_per_group
self.conv1 = nn.Conv2d(3, self.inplanes, kernel_size=7, stride=2, padding=3,
bias=False)
self.bn1 = norm_layer(self.inplanes)
self.relu = nn.ReLU(inplace=True)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.layer1 = self._make_layer(block, 64, layers[0])#对应着con2_x
self.layer2 = self._make_layer(block, 128, layers[1], stride=2,
dilate=replace_stride_with_dilation[0])#对应着con3_x
self.layer3 = self._make_layer(block, 256, layers[2], stride=2,
dilate=replace_stride_with_dilation[1])#对应着con4_x
self.layer4 = self._make_layer(block, 512, layers[3], stride=2,
dilate=replace_stride_with_dilation[2])#对应着con5_x
self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
self.fc = nn.Linear(512 * block.expansion, num_classes)
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
elif isinstance(m, (nn.BatchNorm2d, nn.GroupNorm)):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
# Zero-initialize the last BN in each residual branch,
# so that the residual branch starts with zeros, and each residual block behaves like an identity.
# This improves the model by 0.2~0.3% according to https://arxiv.org/abs/1706.02677
if zero_init_residual:
for m in self.modules():
if isinstance(m, Bottleneck):
nn.init.constant_(m.bn3.weight, 0)
elif isinstance(m, BasicBlock):
nn.init.constant_(m.bn2.weight, 0)
#blocks对应着表1中的 [2, 2, 2, 2]之 中的2 这个数 。它由resnet类型决定 block 对应于Bottleneck还是BasicBlock残差块
def _make_layer(self, block, planes, blocks, stride=1, dilate=False):
norm_layer = self._norm_layer
downsample = None
previous_dilation = self.dilation
if dilate:
self.dilation *= stride
stride = 1
if stride != 1 or self.inplanes != planes * block.expansion:
downsample = nn.Sequential(
conv1x1(self.inplanes, planes * block.expansion, stride),
norm_layer(planes * block.expansion),
)
layers = []
layers.append(block(self.inplanes, planes, stride, downsample, self.groups,
self.base_width, previous_dilation, norm_layer))
self.inplanes = planes * block.expansion
for _ in range(1, blocks):
layers.append(block(self.inplanes, planes, groups=self.groups,
base_width=self.base_width, dilation=self.dilation,
norm_layer=norm_layer))
return nn.Sequential(*layers)
def _forward_impl(self, x):
# See note [TorchScript super()]
x = self.conv1(x)#第一次做卷积 对应图1中conv1 x shape [1 64 112 112]
x = self.bn1(x)# 归一化处理了 x shape [1 64 112 112]
x = self.relu(x)# 激活函数
x = self.maxpool(x)#对应图1中的 conv2_x的3x3 maxpool x shape [1 64 56 56]
x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
x = self.layer4(x)
x = self.avgpool(x)
x = torch.flatten(x, 1)
x = self.fc(x)
return x
def forward(self, x):
return self._forward_impl(x)#resnet处理的主函数。x是输入的图像，待处理数据
def _resnet(arch, block, layers, pretrained, progress, **kwargs):
model = ResNet(block, layers, **kwargs)
return model
def resnet18(pretrained=False, progress=True, **kwargs):
r"""ResNet-18 model from
`"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.pdf>`_
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
progress (bool): If True, displays a progress bar of the download to stderr
"""
return _resnet('resnet18', BasicBlock, [2, 2, 2, 2], pretrained, progress,
**kwargs)
def resnet34(pretrained=False, progress=True, **kwargs):
r"""ResNet-34 model from
`"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.pdf>`_
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
progress (bool): If True, displays a progress bar of the download to stderr
"""
return _resnet('resnet34', BasicBlock, [3, 4, 6, 3], pretrained, progress,
**kwargs)
def resnet50(pretrained=False, progress=True, **kwargs):
r"""ResNet-50 model from
`"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.pdf>`_
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
progress (bool): If True, displays a progress bar of the download to stderr
"""
return _resnet('resnet50', Bottleneck, [3, 4, 6, 3], pretrained, progress,
**kwargs)
def resnet101(pretrained=False, progress=True, **kwargs):
r"""ResNet-101 model from
`"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.pdf>`_
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
progress (bool): If True, displays a progress bar of the download to stderr
"""
return _resnet('resnet101', Bottleneck, [3, 4, 23, 3], pretrained, progress,
**kwargs)
def resnet152(pretrained=False, progress=True, **kwargs):
r"""ResNet-152 model from
`"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.pdf>`_
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
progress (bool): If True, displays a progress bar of the download to stderr
"""
return _resnet('resnet152', Bottleneck, [3, 8, 36, 3], pretrained, progress,
**kwargs)
def resnext50_32x4d(pretrained=False, progress=True, **kwargs):
r"""ResNeXt-50 32x4d model from
`"Aggregated Residual Transformation for Deep Neural Networks" <https://arxiv.org/pdf/1611.05431.pdf>`_
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
progress (bool): If True, displays a progress bar of the download to stderr
"""
kwargs['groups'] = 32
kwargs['width_per_group'] = 4
return _resnet('resnext50_32x4d', Bottleneck, [3, 4, 6, 3],
pretrained, progress, **kwargs)
def resnext101_32x8d(pretrained=False, progress=True, **kwargs):
r"""ResNeXt-101 32x8d model from
`"Aggregated Residual Transformation for Deep Neural Networks" <https://arxiv.org/pdf/1611.05431.pdf>`_
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
progress (bool): If True, displays a progress bar of the download to stderr
"""
kwargs['groups'] = 32
kwargs['width_per_group'] = 8
return _resnet('resnext101_32x8d', Bottleneck, [3, 4, 23, 3],
pretrained, progress, **kwargs)
def wide_resnet50_2(pretrained=False, progress=True, **kwargs):
r"""Wide ResNet-50-2 model from
`"Wide Residual Networks" <https://arxiv.org/pdf/1605.07146.pdf>`_
The model is the same as ResNet except for the bottleneck number of channels
which is twice larger in every block. The number of channels in outer 1x1
convolutions is the same, e.g. last block in ResNet-50 has 2048-512-2048
channels, and in Wide ResNet-50-2 has 2048-1024-2048.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
progress (bool): If True, displays a progress bar of the download to stderr
"""
kwargs['width_per_group'] = 64 * 2
return _resnet('wide_resnet50_2', Bottleneck, [3, 4, 6, 3],
pretrained, progress, **kwargs)
def wide_resnet101_2(pretrained=False, progress=True, **kwargs):
r"""Wide ResNet-101-2 model from
`"Wide Residual Networks" <https://arxiv.org/pdf/1605.07146.pdf>`_
The model is the same as ResNet except for the bottleneck number of channels
which is twice larger in every block. The number of channels in outer 1x1
convolutions is the same, e.g. last block in ResNet-50 has 2048-512-2048
channels, and in Wide ResNet-50-2 has 2048-1024-2048.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
progress (bool): If True, displays a progress bar of the download to stderr
"""
kwargs['width_per_group'] = 64 * 2
return _resnet('wide_resnet101_2', Bottleneck, [3, 4, 23, 3],
pretrained, progress, **kwargs)
def test():
net = resnet18()
print("0000000000")
img = torch.randn(1,3,224,224)
#out = img.convert("RGB")
y = net(img)
print("11111111111")
print(y.size())
if __name__ == '__main__':
test()
https://github.com/SnailTyan/deep-learning-papers-translation 参考资料很详细 很详细
2320
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
