天津市网站建设公司,查询系统入口,房屋设计师破解版,网络工程师好学吗经典卷积神经网络-ResNet
一、背景介绍
残差神经网络(ResNet)是由微软研究院的何恺明、张祥雨、任少卿、孙剑等人提出的。ResNet 在2015 年的ILSVRC#xff08;ImageNet Large Scale Visual Recognition Challenge#xff09;中取得了冠军。残差神经网络的主要贡献是发现了…经典卷积神经网络-ResNet
一、背景介绍
残差神经网络(ResNet)是由微软研究院的何恺明、张祥雨、任少卿、孙剑等人提出的。ResNet 在2015 年的ILSVRCImageNet Large Scale Visual Recognition Challenge中取得了冠军。残差神经网络的主要贡献是发现了“退化现象Degradation”并针对退化现象发明了 “快捷连接Shortcut connection”极大的消除了深度过大的神经网络训练困难问题。神经网络的“深度”首次突破了100层、最大的神经网络甚至超过了1000层。 二、ResNet网络结构
2.0 残差块 配合吴恩达深度学习视频中的图片进行讲解 如图所示Residual block就是将 a [ l ] a^{[l]} a[l]传送到 z l 2 z^{l2} zl2上其相加之后再进行激活得到 a [ l 2 ] a^{[l2]} a[l2]。这一步骤称为skip connection即指 a [ l ] a^{[l]} a[l]跳过一层或好几层从而将信息传递到神经网络的更深层。所以构建一个ResNet网络就是通过将很多这样的残差块堆积在一起形成一个深度神经网络。
那么引入残差块为什么有效呢 一个直观上的理解 如图所示假设我们给我们的神经网络再增加两层我们要得到 a [ l 2 ] a^{[l2]} a[l2]我们通过增加一个残差块来完成。这时 a [ l 2 ] g ( z [ l 2 ] a [ l ] ) g ( w [ l 2 ] a [ l 1 ] a [ l ] ) a^{[l2]}g(z^{[l2]}a^{[l]})g(w^{[l2]}a^{[l1]}a^{}[l]) a[l2]g(z[l2]a[l])g(w[l2]a[l1]a[l])如果我们应用了L2正则化此时权重参数会减小我们可以极端的假设 w [ l 2 ] 0 b [ l 2 ] 0 w^{[l2]}0b^{[l2]}0 w[l2]0b[l2]0那么得到 a [ l 2 ] g ( a [ l ] ) a [ l ] a^{[l2]}g(a^{[l]})a^{[l]} a[l2]g(a[l])a[l]因为使用的是ReLU激活函数非负的值激活后为原来的值 a [ l ] a^{[l]} a[l]已经经过ReLU激活过了所以全为非负值。这意味着即使给神经网络增加了两层它的效果并不逊色于更简单的神经网络。所以给大型的神经网络添加残差块来增加网络深度并不会影响网络的表现。如果我们增加的这两层碰巧能学习到一些有用的信息那么它就比原来的神经网络表现的更好。
论文中ResNet层数在34及以下和50及以上时采用的是不同的残差块。下面我们分别介绍
2.1 ResNet-34 如上图所示是ResNet-34以下采用的残差块我们将其称作BasicBlock。
ResNet-34的网络结构如下图中实线表示通道数没有变化虚线表示通道数发生了变化。 其具体的网络结构如下表 2.2 ResNet-50 如图所示是ResNet-50以上采用的残差块我们将其称作Bottleneck使用了1 × 1的卷积来进行通道数的改变减小计算量。其具体的网络结构见上面的表。
三、论文部分解读 论文中的第一张图就表明了更深层的“plain”神经网络即不用Residual Learning的错误率在训练集和测试集上甚至比层数少的“plain”神经网络还要高所以就引出了问题训练很深的网络是一个很难的问题。 论文中的这张图就表明了使用Residual Learning后训练更深层的神经网络效果会变得更好。 论文中处理残差连接中输入和输出不对等的解决方法 添加一些额外的0使得输入和输出的形状可以对应起来可以做相加。输入和输出不对等的时候使用1 × 1的卷积操作来做投影目前都是这种方法所有的地方都使用1 × 1的卷积来做投影计算量太大没必要 论文最主要的是提出了residual结构残差结构并搭建超深的网络结构(突破1000层) 使用了大量BN来加速训练(丢弃dropout) 论文中对CIFAR10数据集做了大量实验验证其效果最后还将ResNet用到了目标检测领域
三、ResNet-18的Pytorch实现
import torch
import torch.nn as nn
import torchsummary# BasicBlock
class BasicBlock(nn.Module):def __init__(self, in_channels, out_channels, stride1):super(BasicBlock, self).__init__()# 第一个卷积有可能要进行下采样 即将输出通道翻倍 输出数据大小全部减半# 所以我们让第一个卷积的stride设置为可传入的参数# 如果要进行BN 卷积就不需要加偏置self.conv1 nn.Conv2d(in_channels, out_channels, kernel_size3, stridestride, padding1, biasFalse)self.bn1 nn.BatchNorm2d(out_channels)self.relu nn.ReLU(inplaceTrue)# 第二个卷积保持尺寸和通道数self.conv2 nn.Conv2d(out_channels, out_channels, kernel_size3, stride1, padding1, biasFalse)self.bn2 nn.BatchNorm2d(out_channels)# 如果最后输入和输出的通道数不一样 那么就用1 × 1的卷积调节输入 方便后面能和输出相加# shortcut操作也是downsample(下采样) 即将输出通道翻倍 输出数据大小全部减半# 这一步主要做的就是为了能让最后的输出数据和输入数据连接上 即相加self.shortcut nn.Sequential()if stride ! 1 or in_channels ! out_channels:self.shortcut nn.Sequential(nn.Conv2d(in_channels, out_channels, stridestride, kernel_size1, biasFalse),nn.BatchNorm2d(out_channels))def forward(self, x):# 记录identityidentity xout self.conv1(x)out self.bn1(out)out self.relu(out)out self.conv2(out)out self.bn2(out)# 进行残差连接out self.shortcut(identity)# 残差连接之后激活out self.relu(out)return out# ResNet-18
class ResNet18(nn.Module):def __init__(self, num_classes1000):super(ResNet18, self).__init__()# output_size [(input_size - kernel_size 2padding) / stride] 1# 112 [(224 - 7 2padding) / stride] 1 - padding 3self.conv1 nn.Conv2d(3, 64, kernel_size7, stride2, padding3, biasFalse)self.bn1 nn.BatchNorm2d(64)self.relu nn.ReLU(inplaceTrue)# 56 [(112 - 3 2padding) / 2] 1 - padding 1self.maxpool nn.MaxPool2d(kernel_size3, stride2, padding1)self.layer1 self._make_layer(in_channels64, out_channels64, blocks2, stride1)self.layer2 self._make_layer(in_channels64, out_channels128, blocks2, stride2)self.layer3 self._make_layer(in_channels128, out_channels256, blocks2, stride2)self.layer4 self._make_layer(in_channels256, out_channels512, blocks2, stride2)# 平均池化 参数就是out_sizeself.avgpool nn.AdaptiveAvgPool2d((1, 1))self.fc nn.Linear(512, num_classes)def _make_layer(self, in_channels, out_channels, blocks, stride1):layer []# 因为第一个残差块的输入通道可能与输出通道不同 所以单独拿出来赋值layer.append(BasicBlock(in_channels, out_channels, stride))for _ in range(1, blocks):layer.append(BasicBlock(out_channels, out_channels))return nn.Sequential(*layer)def forward(self, x):out self.conv1(x)out self.bn1(out)out self.relu(out)out self.maxpool(out)out self.layer1(out)out self.layer2(out)out self.layer3(out)out self.layer4(out)out self.avgpool(out)out torch.flatten(out, 1)out self.fc(out)return outif __name__ __main__:DEVICE cuda if torch.cuda.is_available() else cpumodel (ResNet18())model.to(DEVICE)# print(model)print(torch.cuda.is_available())torchsummary.summary(model, (3, 224, 224), 64)
主要注意点是
BasicBlock34层以下的残差块中残差连接的方法注意输入和输出的通道数用1×1的卷积做好尺寸和维度对齐。使用_make_layer()函数批量生成残差块。
在控制台输出网络结构
ResNet18((conv1): Conv2d(3, 64, kernel_size(7, 7), stride(2, 2), padding(3, 3), biasFalse)(bn1): BatchNorm2d(64, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(relu): ReLU(inplaceTrue)(maxpool): MaxPool2d(kernel_size3, stride2, padding1, dilation1, ceil_modeFalse)(layer1): Sequential((0): BasicBlock((conv1): Conv2d(64, 64, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn1): BatchNorm2d(64, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(relu): ReLU(inplaceTrue)(conv2): Conv2d(64, 64, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn2): BatchNorm2d(64, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(shortcut): Sequential())(1): BasicBlock((conv1): Conv2d(64, 64, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn1): BatchNorm2d(64, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(relu): ReLU(inplaceTrue)(conv2): Conv2d(64, 64, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn2): BatchNorm2d(64, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(shortcut): Sequential()))(layer2): Sequential((0): BasicBlock((conv1): Conv2d(64, 128, kernel_size(3, 3), stride(2, 2), padding(1, 1), biasFalse)(bn1): BatchNorm2d(128, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(relu): ReLU(inplaceTrue)(conv2): Conv2d(128, 128, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn2): BatchNorm2d(128, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(shortcut): Sequential((0): Conv2d(64, 128, kernel_size(1, 1), stride(2, 2), biasFalse)(1): BatchNorm2d(128, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)))(1): BasicBlock((conv1): Conv2d(128, 128, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn1): BatchNorm2d(128, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(relu): ReLU(inplaceTrue)(conv2): Conv2d(128, 128, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn2): BatchNorm2d(128, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(shortcut): Sequential()))(layer3): Sequential((0): BasicBlock((conv1): Conv2d(128, 256, kernel_size(3, 3), stride(2, 2), padding(1, 1), biasFalse)(bn1): BatchNorm2d(256, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(relu): ReLU(inplaceTrue)(conv2): Conv2d(256, 256, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn2): BatchNorm2d(256, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(shortcut): Sequential((0): Conv2d(128, 256, kernel_size(1, 1), stride(2, 2), biasFalse)(1): BatchNorm2d(256, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)))(1): BasicBlock((conv1): Conv2d(256, 256, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn1): BatchNorm2d(256, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(relu): ReLU(inplaceTrue)(conv2): Conv2d(256, 256, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn2): BatchNorm2d(256, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(shortcut): Sequential()))(layer4): Sequential((0): BasicBlock((conv1): Conv2d(256, 512, kernel_size(3, 3), stride(2, 2), padding(1, 1), biasFalse)(bn1): BatchNorm2d(512, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(relu): ReLU(inplaceTrue)(conv2): Conv2d(512, 512, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn2): BatchNorm2d(512, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(shortcut): Sequential((0): Conv2d(256, 512, kernel_size(1, 1), stride(2, 2), biasFalse)(1): BatchNorm2d(512, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)))(1): BasicBlock((conv1): Conv2d(512, 512, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn1): BatchNorm2d(512, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(relu): ReLU(inplaceTrue)(conv2): Conv2d(512, 512, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn2): BatchNorm2d(512, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(shortcut): Sequential()))(avgpool): AdaptiveAvgPool2d(output_size(1, 1))(fc): Linear(in_features512, out_features1000, biasTrue)
)使用torchsummary来测试网络
----------------------------------------------------------------Layer (type) Output Shape Param #
Conv2d-1 [64, 64, 112, 112] 9,408BatchNorm2d-2 [64, 64, 112, 112] 128ReLU-3 [64, 64, 112, 112] 0MaxPool2d-4 [64, 64, 56, 56] 0Conv2d-5 [64, 64, 56, 56] 36,864BatchNorm2d-6 [64, 64, 56, 56] 128ReLU-7 [64, 64, 56, 56] 0Conv2d-8 [64, 64, 56, 56] 36,864BatchNorm2d-9 [64, 64, 56, 56] 128ReLU-10 [64, 64, 56, 56] 0BasicBlock-11 [64, 64, 56, 56] 0Conv2d-12 [64, 64, 56, 56] 36,864BatchNorm2d-13 [64, 64, 56, 56] 128ReLU-14 [64, 64, 56, 56] 0Conv2d-15 [64, 64, 56, 56] 36,864BatchNorm2d-16 [64, 64, 56, 56] 128ReLU-17 [64, 64, 56, 56] 0BasicBlock-18 [64, 64, 56, 56] 0Conv2d-19 [64, 128, 28, 28] 73,728BatchNorm2d-20 [64, 128, 28, 28] 256ReLU-21 [64, 128, 28, 28] 0Conv2d-22 [64, 128, 28, 28] 147,456BatchNorm2d-23 [64, 128, 28, 28] 256Conv2d-24 [64, 128, 28, 28] 8,192BatchNorm2d-25 [64, 128, 28, 28] 256ReLU-26 [64, 128, 28, 28] 0BasicBlock-27 [64, 128, 28, 28] 0Conv2d-28 [64, 128, 28, 28] 147,456BatchNorm2d-29 [64, 128, 28, 28] 256ReLU-30 [64, 128, 28, 28] 0Conv2d-31 [64, 128, 28, 28] 147,456BatchNorm2d-32 [64, 128, 28, 28] 256ReLU-33 [64, 128, 28, 28] 0BasicBlock-34 [64, 128, 28, 28] 0Conv2d-35 [64, 256, 14, 14] 294,912BatchNorm2d-36 [64, 256, 14, 14] 512ReLU-37 [64, 256, 14, 14] 0Conv2d-38 [64, 256, 14, 14] 589,824BatchNorm2d-39 [64, 256, 14, 14] 512Conv2d-40 [64, 256, 14, 14] 32,768BatchNorm2d-41 [64, 256, 14, 14] 512ReLU-42 [64, 256, 14, 14] 0BasicBlock-43 [64, 256, 14, 14] 0Conv2d-44 [64, 256, 14, 14] 589,824BatchNorm2d-45 [64, 256, 14, 14] 512ReLU-46 [64, 256, 14, 14] 0Conv2d-47 [64, 256, 14, 14] 589,824BatchNorm2d-48 [64, 256, 14, 14] 512ReLU-49 [64, 256, 14, 14] 0BasicBlock-50 [64, 256, 14, 14] 0Conv2d-51 [64, 512, 7, 7] 1,179,648BatchNorm2d-52 [64, 512, 7, 7] 1,024ReLU-53 [64, 512, 7, 7] 0Conv2d-54 [64, 512, 7, 7] 2,359,296BatchNorm2d-55 [64, 512, 7, 7] 1,024Conv2d-56 [64, 512, 7, 7] 131,072BatchNorm2d-57 [64, 512, 7, 7] 1,024ReLU-58 [64, 512, 7, 7] 0BasicBlock-59 [64, 512, 7, 7] 0Conv2d-60 [64, 512, 7, 7] 2,359,296BatchNorm2d-61 [64, 512, 7, 7] 1,024ReLU-62 [64, 512, 7, 7] 0Conv2d-63 [64, 512, 7, 7] 2,359,296BatchNorm2d-64 [64, 512, 7, 7] 1,024ReLU-65 [64, 512, 7, 7] 0BasicBlock-66 [64, 512, 7, 7] 0
AdaptiveAvgPool2d-67 [64, 512, 1, 1] 0Linear-68 [64, 1000] 513,000Total params: 11,689,512
Trainable params: 11,689,512
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 36.75
Forward/backward pass size (MB): 4018.74
Params size (MB): 44.59
Estimated Total Size (MB): 4100.08
----------------------------------------------------------------四、ResNet-50的Pytorch实现
import torch
import torch.nn as nn
import torchsummary# Bottleneck
class Bottleneck(nn.Module):# expansion 4因为Bottleneck中每个残差结构输出维度都是输入维度的4倍expansion 4def __init__(self, in_channels, out_channels, stride1):super(Bottleneck, self).__init__()# 注意这里1×1的卷积不用paddingself.conv1 nn.Conv2d(in_channels, out_channels, kernel_size1, stridestride, biasFalse)self.bn1 nn.BatchNorm2d(out_channels)# 维持特征图尺寸 padding 1self.conv2 nn.Conv2d(out_channels, out_channels, kernel_size3, stride1, padding1, biasFalse)self.bn2 nn.BatchNorm2d(out_channels)# 注意这里1×1的卷积不用paddingself.conv3 nn.Conv2d(out_channels, out_channels * self.expansion, kernel_size1, stride1, biasFalse)self.bn3 nn.BatchNorm2d(out_channels * self.expansion)self.relu nn.ReLU(inplaceTrue)self.shortcut nn.Sequential()if stride ! 1 or in_channels ! out_channels * self.expansion:self.shortcut nn.Sequential(nn.Conv2d(in_channels, out_channels * self.expansion, stridestride, kernel_size1, biasFalse),nn.BatchNorm2d(out_channels * self.expansion))def forward(self, x):identity xout 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)# 残差连接out self.shortcut(identity)out self.relu(out)return out# ResNet50
class ResNet50(nn.Module):def __init__(self, num_classes1000):super(ResNet50, self).__init__()# output_size [(input_size - kernel_size 2padding) / stride] 1# 112 [(224 - 7 2padding) / stride] 1 - padding 3self.conv1 nn.Conv2d(3, 64, kernel_size7, stride2, padding3, biasFalse)self.bn1 nn.BatchNorm2d(64)self.relu nn.ReLU(inplaceTrue)# 56 [(112 - 3 2padding) / 2] 1 - padding 1self.maxpool nn.MaxPool2d(kernel_size3, stride2, padding1)self.layer1 self._make_layer(64, 64, blocks3, stride1)self.layer2 self._make_layer(256, 128, blocks4, stride2)self.layer3 self._make_layer(512, 256, blocks6, stride2)self.layer4 self._make_layer(1024, 512, blocks3, stride2)# 平均池化 参数就是out_sizeself.avgpool nn.AdaptiveAvgPool2d((1, 1))self.fc nn.Linear(2048, num_classes)def _make_layer(self, in_channels, out_channels, blocks, stride1):layer []# 因为第一个残差块的输入通道可能与输出通道不同 所以单独拿出来赋值layer.append(Bottleneck(in_channels, out_channels, stride))for _ in range(1, blocks):# 接下来的每一个其输入通道都是输出的四倍layer.append(Bottleneck(out_channels * 4, out_channels))return nn.Sequential(*layer)def forward(self, x):out self.conv1(x)out self.bn1(out)out self.relu(out)out self.maxpool(out)out self.layer1(out)out self.layer2(out)out self.layer3(out)out self.layer4(out)out self.avgpool(out)out torch.flatten(out, 1)out self.fc(out)return outif __name__ __main__:DEVICE cuda if torch.cuda.is_available() else cpumodel ResNet50()model.to(DEVICE)# print(model)torchsummary.summary(model, (3, 224, 224), 64)主要注意点是 Bottleneck50层以上残差块中块与块直接连接的通道数问题。在BasicBlock中由于两个相同的块在连接的时候通道数是相同的而Bottleneck中两个相同的块在连接的时候其通道数相差四倍。即下面这段代码 for _ in range(1, blocks):# 接下来的每一个其输入通道都是输出的四倍layer.append(Bottleneck(out_channels * 4, out_channels))注意最后全连接的通道数ResNet50以上的最后全连接的in_features为2048。 注意在残差连接的时候shortcut调整的维度一定要和输出维度对上即下面这段代码 self.shortcut nn.Sequential()
if stride ! 1 or in_channels ! out_channels * self.expansion:self.shortcut nn.Sequential(nn.Conv2d(in_channels, out_channels * self.expansion, stridestride, kernel_size1, biasFalse),nn.BatchNorm2d(out_channels * self.expansion))写代码的时候要注意只有每一堆残差块结构中的第一个残差块的第一个卷积操作的stride为2其余都为1除了第一堆残差块要维持尺度不变即 self.layer1 self._make_layer(64, 64, blocks3, stride1)在控制台输出网络结构
ResNet50((conv1): Conv2d(3, 64, kernel_size(7, 7), stride(2, 2), padding(3, 3), biasFalse)(bn1): BatchNorm2d(64, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(relu): ReLU(inplaceTrue)(maxpool): MaxPool2d(kernel_size3, stride2, padding1, dilation1, ceil_modeFalse)(layer1): Sequential((0): Bottleneck((conv1): Conv2d(64, 64, kernel_size(1, 1), stride(1, 1), biasFalse)(bn1): BatchNorm2d(64, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(conv2): Conv2d(64, 64, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn2): BatchNorm2d(64, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(conv3): Conv2d(64, 256, kernel_size(1, 1), stride(1, 1), biasFalse)(bn3): BatchNorm2d(256, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(relu): ReLU(inplaceTrue)(shortcut): Sequential((0): Conv2d(64, 256, kernel_size(1, 1), stride(1, 1), biasFalse)(1): BatchNorm2d(256, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)))(1): Bottleneck((conv1): Conv2d(256, 64, kernel_size(1, 1), stride(1, 1), biasFalse)(bn1): BatchNorm2d(64, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(conv2): Conv2d(64, 64, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn2): BatchNorm2d(64, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(conv3): Conv2d(64, 256, kernel_size(1, 1), stride(1, 1), biasFalse)(bn3): BatchNorm2d(256, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(relu): ReLU(inplaceTrue)(shortcut): Sequential())(2): Bottleneck((conv1): Conv2d(256, 64, kernel_size(1, 1), stride(1, 1), biasFalse)(bn1): BatchNorm2d(64, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(conv2): Conv2d(64, 64, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn2): BatchNorm2d(64, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(conv3): Conv2d(64, 256, kernel_size(1, 1), stride(1, 1), biasFalse)(bn3): BatchNorm2d(256, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(relu): ReLU(inplaceTrue)(shortcut): Sequential()))(layer2): Sequential((0): Bottleneck((conv1): Conv2d(256, 128, kernel_size(1, 1), stride(2, 2), biasFalse)(bn1): BatchNorm2d(128, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(conv2): Conv2d(128, 128, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn2): BatchNorm2d(128, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(conv3): Conv2d(128, 512, kernel_size(1, 1), stride(1, 1), biasFalse)(bn3): BatchNorm2d(512, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(relu): ReLU(inplaceTrue)(shortcut): Sequential((0): Conv2d(256, 512, kernel_size(1, 1), stride(2, 2), biasFalse)(1): BatchNorm2d(512, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)))(1): Bottleneck((conv1): Conv2d(512, 128, kernel_size(1, 1), stride(1, 1), biasFalse)(bn1): BatchNorm2d(128, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(conv2): Conv2d(128, 128, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn2): BatchNorm2d(128, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(conv3): Conv2d(128, 512, kernel_size(1, 1), stride(1, 1), biasFalse)(bn3): BatchNorm2d(512, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(relu): ReLU(inplaceTrue)(shortcut): Sequential())(2): Bottleneck((conv1): Conv2d(512, 128, kernel_size(1, 1), stride(1, 1), biasFalse)(bn1): BatchNorm2d(128, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(conv2): Conv2d(128, 128, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn2): BatchNorm2d(128, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(conv3): Conv2d(128, 512, kernel_size(1, 1), stride(1, 1), biasFalse)(bn3): BatchNorm2d(512, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(relu): ReLU(inplaceTrue)(shortcut): Sequential())(3): Bottleneck((conv1): Conv2d(512, 128, kernel_size(1, 1), stride(1, 1), biasFalse)(bn1): BatchNorm2d(128, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(conv2): Conv2d(128, 128, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn2): BatchNorm2d(128, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(conv3): Conv2d(128, 512, kernel_size(1, 1), stride(1, 1), biasFalse)(bn3): BatchNorm2d(512, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(relu): ReLU(inplaceTrue)(shortcut): Sequential()))(layer3): Sequential((0): Bottleneck((conv1): Conv2d(512, 256, kernel_size(1, 1), stride(2, 2), biasFalse)(bn1): BatchNorm2d(256, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(conv2): Conv2d(256, 256, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn2): BatchNorm2d(256, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(conv3): Conv2d(256, 1024, kernel_size(1, 1), stride(1, 1), biasFalse)(bn3): BatchNorm2d(1024, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(relu): ReLU(inplaceTrue)(shortcut): Sequential((0): Conv2d(512, 1024, kernel_size(1, 1), stride(2, 2), biasFalse)(1): BatchNorm2d(1024, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)))(1): Bottleneck((conv1): Conv2d(1024, 256, kernel_size(1, 1), stride(1, 1), biasFalse)(bn1): BatchNorm2d(256, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(conv2): Conv2d(256, 256, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn2): BatchNorm2d(256, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(conv3): Conv2d(256, 1024, kernel_size(1, 1), stride(1, 1), biasFalse)(bn3): BatchNorm2d(1024, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(relu): ReLU(inplaceTrue)(shortcut): Sequential())(2): Bottleneck((conv1): Conv2d(1024, 256, kernel_size(1, 1), stride(1, 1), biasFalse)(bn1): BatchNorm2d(256, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(conv2): Conv2d(256, 256, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn2): BatchNorm2d(256, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(conv3): Conv2d(256, 1024, kernel_size(1, 1), stride(1, 1), biasFalse)(bn3): BatchNorm2d(1024, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(relu): ReLU(inplaceTrue)(shortcut): Sequential())(3): Bottleneck((conv1): Conv2d(1024, 256, kernel_size(1, 1), stride(1, 1), biasFalse)(bn1): BatchNorm2d(256, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(conv2): Conv2d(256, 256, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn2): BatchNorm2d(256, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(conv3): Conv2d(256, 1024, kernel_size(1, 1), stride(1, 1), biasFalse)(bn3): BatchNorm2d(1024, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(relu): ReLU(inplaceTrue)(shortcut): Sequential())(4): Bottleneck((conv1): Conv2d(1024, 256, kernel_size(1, 1), stride(1, 1), biasFalse)(bn1): BatchNorm2d(256, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(conv2): Conv2d(256, 256, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn2): BatchNorm2d(256, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(conv3): Conv2d(256, 1024, kernel_size(1, 1), stride(1, 1), biasFalse)(bn3): BatchNorm2d(1024, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(relu): ReLU(inplaceTrue)(shortcut): Sequential())(5): Bottleneck((conv1): Conv2d(1024, 256, kernel_size(1, 1), stride(1, 1), biasFalse)(bn1): BatchNorm2d(256, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(conv2): Conv2d(256, 256, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn2): BatchNorm2d(256, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(conv3): Conv2d(256, 1024, kernel_size(1, 1), stride(1, 1), biasFalse)(bn3): BatchNorm2d(1024, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(relu): ReLU(inplaceTrue)(shortcut): Sequential()))(layer4): Sequential((0): Bottleneck((conv1): Conv2d(1024, 512, kernel_size(1, 1), stride(2, 2), biasFalse)(bn1): BatchNorm2d(512, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(conv2): Conv2d(512, 512, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn2): BatchNorm2d(512, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(conv3): Conv2d(512, 2048, kernel_size(1, 1), stride(1, 1), biasFalse)(bn3): BatchNorm2d(2048, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(relu): ReLU(inplaceTrue)(shortcut): Sequential((0): Conv2d(1024, 2048, kernel_size(1, 1), stride(2, 2), biasFalse)(1): BatchNorm2d(2048, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)))(1): Bottleneck((conv1): Conv2d(2048, 512, kernel_size(1, 1), stride(1, 1), biasFalse)(bn1): BatchNorm2d(512, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(conv2): Conv2d(512, 512, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn2): BatchNorm2d(512, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(conv3): Conv2d(512, 2048, kernel_size(1, 1), stride(1, 1), biasFalse)(bn3): BatchNorm2d(2048, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(relu): ReLU(inplaceTrue)(shortcut): Sequential())(2): Bottleneck((conv1): Conv2d(2048, 512, kernel_size(1, 1), stride(1, 1), biasFalse)(bn1): BatchNorm2d(512, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(conv2): Conv2d(512, 512, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn2): BatchNorm2d(512, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(conv3): Conv2d(512, 2048, kernel_size(1, 1), stride(1, 1), biasFalse)(bn3): BatchNorm2d(2048, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(relu): ReLU(inplaceTrue)(shortcut): Sequential()))(avgpool): AdaptiveAvgPool2d(output_size(1, 1))(fc): Linear(in_features2048, out_features1000, biasTrue)
)使用torchsummary来测试网络
----------------------------------------------------------------Layer (type) Output Shape Param #
Conv2d-1 [64, 64, 112, 112] 9,408BatchNorm2d-2 [64, 64, 112, 112] 128ReLU-3 [64, 64, 112, 112] 0MaxPool2d-4 [64, 64, 56, 56] 0Conv2d-5 [64, 64, 56, 56] 4,096BatchNorm2d-6 [64, 64, 56, 56] 128ReLU-7 [64, 64, 56, 56] 0Conv2d-8 [64, 64, 56, 56] 36,864BatchNorm2d-9 [64, 64, 56, 56] 128ReLU-10 [64, 64, 56, 56] 0Conv2d-11 [64, 256, 56, 56] 16,384BatchNorm2d-12 [64, 256, 56, 56] 512Conv2d-13 [64, 256, 56, 56] 16,384BatchNorm2d-14 [64, 256, 56, 56] 512ReLU-15 [64, 256, 56, 56] 0Bottleneck-16 [64, 256, 56, 56] 0Conv2d-17 [64, 64, 56, 56] 16,384BatchNorm2d-18 [64, 64, 56, 56] 128ReLU-19 [64, 64, 56, 56] 0Conv2d-20 [64, 64, 56, 56] 36,864BatchNorm2d-21 [64, 64, 56, 56] 128ReLU-22 [64, 64, 56, 56] 0Conv2d-23 [64, 256, 56, 56] 16,384BatchNorm2d-24 [64, 256, 56, 56] 512ReLU-25 [64, 256, 56, 56] 0Bottleneck-26 [64, 256, 56, 56] 0Conv2d-27 [64, 64, 56, 56] 16,384BatchNorm2d-28 [64, 64, 56, 56] 128ReLU-29 [64, 64, 56, 56] 0Conv2d-30 [64, 64, 56, 56] 36,864BatchNorm2d-31 [64, 64, 56, 56] 128ReLU-32 [64, 64, 56, 56] 0Conv2d-33 [64, 256, 56, 56] 16,384BatchNorm2d-34 [64, 256, 56, 56] 512ReLU-35 [64, 256, 56, 56] 0Bottleneck-36 [64, 256, 56, 56] 0Conv2d-37 [64, 128, 28, 28] 32,768BatchNorm2d-38 [64, 128, 28, 28] 256ReLU-39 [64, 128, 28, 28] 0Conv2d-40 [64, 128, 28, 28] 147,456BatchNorm2d-41 [64, 128, 28, 28] 256ReLU-42 [64, 128, 28, 28] 0Conv2d-43 [64, 512, 28, 28] 65,536BatchNorm2d-44 [64, 512, 28, 28] 1,024Conv2d-45 [64, 512, 28, 28] 131,072BatchNorm2d-46 [64, 512, 28, 28] 1,024ReLU-47 [64, 512, 28, 28] 0Bottleneck-48 [64, 512, 28, 28] 0Conv2d-49 [64, 128, 28, 28] 65,536BatchNorm2d-50 [64, 128, 28, 28] 256ReLU-51 [64, 128, 28, 28] 0Conv2d-52 [64, 128, 28, 28] 147,456BatchNorm2d-53 [64, 128, 28, 28] 256ReLU-54 [64, 128, 28, 28] 0Conv2d-55 [64, 512, 28, 28] 65,536BatchNorm2d-56 [64, 512, 28, 28] 1,024ReLU-57 [64, 512, 28, 28] 0Bottleneck-58 [64, 512, 28, 28] 0Conv2d-59 [64, 128, 28, 28] 65,536BatchNorm2d-60 [64, 128, 28, 28] 256ReLU-61 [64, 128, 28, 28] 0Conv2d-62 [64, 128, 28, 28] 147,456BatchNorm2d-63 [64, 128, 28, 28] 256ReLU-64 [64, 128, 28, 28] 0Conv2d-65 [64, 512, 28, 28] 65,536BatchNorm2d-66 [64, 512, 28, 28] 1,024ReLU-67 [64, 512, 28, 28] 0Bottleneck-68 [64, 512, 28, 28] 0Conv2d-69 [64, 128, 28, 28] 65,536BatchNorm2d-70 [64, 128, 28, 28] 256ReLU-71 [64, 128, 28, 28] 0Conv2d-72 [64, 128, 28, 28] 147,456BatchNorm2d-73 [64, 128, 28, 28] 256ReLU-74 [64, 128, 28, 28] 0Conv2d-75 [64, 512, 28, 28] 65,536BatchNorm2d-76 [64, 512, 28, 28] 1,024ReLU-77 [64, 512, 28, 28] 0Bottleneck-78 [64, 512, 28, 28] 0Conv2d-79 [64, 256, 14, 14] 131,072BatchNorm2d-80 [64, 256, 14, 14] 512ReLU-81 [64, 256, 14, 14] 0Conv2d-82 [64, 256, 14, 14] 589,824BatchNorm2d-83 [64, 256, 14, 14] 512ReLU-84 [64, 256, 14, 14] 0Conv2d-85 [64, 1024, 14, 14] 262,144BatchNorm2d-86 [64, 1024, 14, 14] 2,048Conv2d-87 [64, 1024, 14, 14] 524,288BatchNorm2d-88 [64, 1024, 14, 14] 2,048ReLU-89 [64, 1024, 14, 14] 0Bottleneck-90 [64, 1024, 14, 14] 0Conv2d-91 [64, 256, 14, 14] 262,144BatchNorm2d-92 [64, 256, 14, 14] 512ReLU-93 [64, 256, 14, 14] 0Conv2d-94 [64, 256, 14, 14] 589,824BatchNorm2d-95 [64, 256, 14, 14] 512ReLU-96 [64, 256, 14, 14] 0Conv2d-97 [64, 1024, 14, 14] 262,144BatchNorm2d-98 [64, 1024, 14, 14] 2,048ReLU-99 [64, 1024, 14, 14] 0Bottleneck-100 [64, 1024, 14, 14] 0Conv2d-101 [64, 256, 14, 14] 262,144BatchNorm2d-102 [64, 256, 14, 14] 512ReLU-103 [64, 256, 14, 14] 0Conv2d-104 [64, 256, 14, 14] 589,824BatchNorm2d-105 [64, 256, 14, 14] 512ReLU-106 [64, 256, 14, 14] 0Conv2d-107 [64, 1024, 14, 14] 262,144BatchNorm2d-108 [64, 1024, 14, 14] 2,048ReLU-109 [64, 1024, 14, 14] 0Bottleneck-110 [64, 1024, 14, 14] 0Conv2d-111 [64, 256, 14, 14] 262,144BatchNorm2d-112 [64, 256, 14, 14] 512ReLU-113 [64, 256, 14, 14] 0Conv2d-114 [64, 256, 14, 14] 589,824BatchNorm2d-115 [64, 256, 14, 14] 512ReLU-116 [64, 256, 14, 14] 0Conv2d-117 [64, 1024, 14, 14] 262,144BatchNorm2d-118 [64, 1024, 14, 14] 2,048ReLU-119 [64, 1024, 14, 14] 0Bottleneck-120 [64, 1024, 14, 14] 0Conv2d-121 [64, 256, 14, 14] 262,144BatchNorm2d-122 [64, 256, 14, 14] 512ReLU-123 [64, 256, 14, 14] 0Conv2d-124 [64, 256, 14, 14] 589,824BatchNorm2d-125 [64, 256, 14, 14] 512ReLU-126 [64, 256, 14, 14] 0Conv2d-127 [64, 1024, 14, 14] 262,144BatchNorm2d-128 [64, 1024, 14, 14] 2,048ReLU-129 [64, 1024, 14, 14] 0Bottleneck-130 [64, 1024, 14, 14] 0Conv2d-131 [64, 256, 14, 14] 262,144BatchNorm2d-132 [64, 256, 14, 14] 512ReLU-133 [64, 256, 14, 14] 0Conv2d-134 [64, 256, 14, 14] 589,824BatchNorm2d-135 [64, 256, 14, 14] 512ReLU-136 [64, 256, 14, 14] 0Conv2d-137 [64, 1024, 14, 14] 262,144BatchNorm2d-138 [64, 1024, 14, 14] 2,048ReLU-139 [64, 1024, 14, 14] 0Bottleneck-140 [64, 1024, 14, 14] 0Conv2d-141 [64, 512, 7, 7] 524,288BatchNorm2d-142 [64, 512, 7, 7] 1,024ReLU-143 [64, 512, 7, 7] 0Conv2d-144 [64, 512, 7, 7] 2,359,296BatchNorm2d-145 [64, 512, 7, 7] 1,024ReLU-146 [64, 512, 7, 7] 0Conv2d-147 [64, 2048, 7, 7] 1,048,576BatchNorm2d-148 [64, 2048, 7, 7] 4,096Conv2d-149 [64, 2048, 7, 7] 2,097,152BatchNorm2d-150 [64, 2048, 7, 7] 4,096ReLU-151 [64, 2048, 7, 7] 0Bottleneck-152 [64, 2048, 7, 7] 0Conv2d-153 [64, 512, 7, 7] 1,048,576BatchNorm2d-154 [64, 512, 7, 7] 1,024ReLU-155 [64, 512, 7, 7] 0Conv2d-156 [64, 512, 7, 7] 2,359,296BatchNorm2d-157 [64, 512, 7, 7] 1,024ReLU-158 [64, 512, 7, 7] 0Conv2d-159 [64, 2048, 7, 7] 1,048,576BatchNorm2d-160 [64, 2048, 7, 7] 4,096ReLU-161 [64, 2048, 7, 7] 0Bottleneck-162 [64, 2048, 7, 7] 0Conv2d-163 [64, 512, 7, 7] 1,048,576BatchNorm2d-164 [64, 512, 7, 7] 1,024ReLU-165 [64, 512, 7, 7] 0Conv2d-166 [64, 512, 7, 7] 2,359,296BatchNorm2d-167 [64, 512, 7, 7] 1,024ReLU-168 [64, 512, 7, 7] 0Conv2d-169 [64, 2048, 7, 7] 1,048,576BatchNorm2d-170 [64, 2048, 7, 7] 4,096ReLU-171 [64, 2048, 7, 7] 0Bottleneck-172 [64, 2048, 7, 7] 0
AdaptiveAvgPool2d-173 [64, 2048, 1, 1] 0Linear-174 [64, 1000] 2,049,000Total params: 25,557,032
Trainable params: 25,557,032
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 36.75
Forward/backward pass size (MB): 15200.01
Params size (MB): 97.49
Estimated Total Size (MB): 15334.25
----------------------------------------------------------------参考链接 https://link.zhihu.com/?targethttps%3A//arxiv.org/pdf/1512.03385.pdf https://blog.csdn.net/m0_64799972/article/details/132753608 https://blog.csdn.net/m0_50127633/article/details/117200212 https://www.bilibili.com/video/BV1Bo4y1T7Lc/?spm_id_from333.999.0.0vd_sourcec7e390079ff3e10b79e23fb333bea49d
