经典CNN算法解析实战-第J2周：ResNet50V2算法实战与解析

已于 2023-02-22 11:40:19 修改
阅读量601 收藏
点赞数
分类专栏： 365天深度学习训练记录 文章标签： cnn 算法 深度学习
于 2023-02-16 16:32:11 首次发布
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://blog.csdn.net/qq_27889941/article/details/128972639
版权

目录

一、课题背景和开发环境

📌第J2周：ResNet50V2算法实战与解析📌

  • 语言：Python3、Pytorch
  • 📌本周任务：📌
    – 1.请根据本文TensorFlow代码，编写出相应的Pytorch代码（建议使用上周的数据测试一下模型是否构建正确）
    – 2.了解ResNetV2与ResNetV的区别
    – 3.改进思路是否可以迁移到其他地方呢（自由探索）

**🔊注：**从前几周开始训练营的难度逐渐提升，具体体现在不再直接提供源代码。任务中会给大家提供一些算法改进的思路/方向，希望大家这一块可以积极探索。（这个探索的过程很重要，也将学到更多）

二、论文解读

论文原文，何凯明大神在这篇论文中提出了一种新的残差单元。我们将这篇论文中的ResNet结构称为ResNetV2：
Identity Mappings in Deep Residual Networks.pdf

1.ResNetV2结构与ResNet结构对比

ResNet与ResNetV2对比：实线表示测试误差，虚线表示损失
**🧲 改进点： **(a)original表示原始的ResNet的残差结构，(b)proposed表示新的ResNet的残差结构。主要差别就是(a)结构先卷积后进行BN和激活函数计算，最后执行addition后再进行ReLU计算；(b)结构先进性BN和激活函数计算后卷积，把addition后的ReLU计算放到了残差结构内部。

📌 改进结果：作者使用这两种不同的结构再CIFAR-10数据集上做测试，模型用的是1001层的ResNet模型。从图中的结果我们可以看出，(b)proposed的测试集错误率明显更低一些，达到了4.92%的错误率。(a)original的测试集错误率是7.61%。

2.关于残差结构的不同尝试

关于残差结构的不同尝试
(b-f)中的快捷连接被不同的组件阻碍。为了简化插图，我们不显示BN层，这里所有的单位均采用权值层之后的BN层。图中(a-f)都是作者对残差结构的shortcut部分进行的不同尝试，作者对不同shortcut结构的尝试结果如下表所示。

使用ResNet-110在CIFAR-10测试集上的分类错误，对所有残差单元应用了不同类型的shortcut connections。当测试错误差高于20%时，标注为“fail”。
作者用不同的shortcut结构的ResNet-110在CIFAR-10数据集上做测试，发现最原始的(a)original结构是最好的，也就是identity mapping恒等映射是最好的。

3.关于激活的尝试

关于激活的尝试
使用不同激活函数的CIFAR-10测试集上的分类误差(%)。
最好的结果是(e)full pre-activation，其次是(a)original。

三、模型复现

1.Residual Block

tensorFlow

''' 残差块
Arguments:
    x: 输入张量
    filters: integer, filters, of the bottleneck layer.
    kernel_size: default 3, kernel size of the bottleneck layer.
    stride: default 1, stride of the first layer.
    conv_shortcut: default False, use convolution shortcut if True, otherwise identity shortcut.
    name: string, block label.
Returns:
    Output tensor for the residual block.
'''
def block2(x, filters, kernel_size=3, stride=1, conv_shortcut=False, name=None):
    preact = BatchNormalization(name=name+'_preact_bn')(x)
    preact = Activation('relu', name=name+'_preact_relu')(preact)
    
    if conv_shortcut:
        shortcut = Conv2D(4*filters, 1, strides=stride, name=name+'_0_conv')(preact)
    else:
        # 注意后面多的if语句
        shortcut = MaxPooling2D(1, strides=stride)(x) if stride>1 else x
    
    x = Conv2D(filters, 1, strides=1, use_bias=False, name=name+'_1_conv')(preact)
    x = BatchNormalization(name=name+'_1_bn')(x)
    x = Activation('relu', name=name+'_1_relu')(x)
    
    x = ZeroPadding2D(padding=((1, 1), (1, 1)), name=name+'_2_pad')(x)
    x = Conv2D(filters, kernel_size, strides=stride, use_bias=False, name=name+'_2_conv')(x)
    x = BatchNormalization(name=name+'_2_bn')(x)
    x = Activation('relu', name=name+'_2_relu')(x)
    
    x = Conv2D(4*filters, 1, name=name+'_3_conv')(x)
    x = layers.Add(name=name+'_out')([shortcut, x])
    return x

Pytorch

''' Residual Block '''
class Block2(nn.Module):
    def __init__(self, in_channel, filters, kernel_size=3, stride=1, conv_shortcut=False):
        super(Block2, self).__init__()
        self.preact = nn.Sequential(
            nn.BatchNorm2d(in_channel),
            nn.ReLU(True)
        )
        
        self.shortcut = conv_shortcut
        if self.shortcut:
            self.short = nn.Conv2d(in_channel, 4*filters, 1, stride=stride, padding=0, bias=False)
        elif stride>1:
            self.short = nn.MaxPool2d(kernel_size=1, stride=stride, padding=0)
        else:
            self.short = nn.Identity()
        
        self.conv1 = nn.Sequential(
            nn.Conv2d(in_channel, filters, 1, stride=1, bias=False),
            nn.BatchNorm2d(filters),
            nn.ReLU(True)
        )
        self.conv2 = nn.Sequential(
            nn.Conv2d(filters, filters, kernel_size, stride=stride, padding=1, bias=False),
            nn.BatchNorm2d(filters),
            nn.ReLU(True)
        )
        self.conv3 = nn.Conv2d(filters, 4*filters, 1, stride=1, bias=False)
    
    def forward(self, x):
        x1 = self.preact(x)
        if self.shortcut:
            x2 = self.short(x1)
        else:
            x2 = self.short(x)
        x1 = self.conv1(x1)
        x1 = self.conv2(x1)
        x1 = self.conv3(x1)
        x = x1 + x2
        return x

2.堆叠Residual Block

tensorFlow

def stack2(x, filters, blocks, stride1=2, name=None):
    x = block2(x, filters, conv_shortcut=True, name=name+'_block1')
    for i in range(2, blocks):
        x = block2(x, filters, name=name+'_block'+str(i))
    x = block2(x, filters, stride=stride1, name=name+'_block'+str(blocks))
    return x

Pytorch

class Stack2(nn.Module):
    def __init__(self, in_channel, filters, blocks, stride=2):
        super(Stack2, self).__init__()
        self.conv = nn.Sequential()
        self.conv.add_module(str(0), Block2(in_channel, filters, conv_shortcut=True))
        for i in range(1, blocks-1):
            self.conv.add_module(str(i), Block2(4*filters, filters))
        self.conv.add_module(str(blocks-1), Block2(4*filters, filters, stride=stride))
    
    def forward(self, x):
        x = self.conv(x)
        return x

3.ResNet50V2架构复现

ResNet50V2架构复现
tensorFlow

''' 构建ResNet50V2 '''
def ResNet50V2(include_top=True,  # 是否包含位于网络顶部的全链接层
               preact=True,  # 是否使用预激活
               use_bias=True,  # 是否对卷积层使用偏置
               weights='imagenet',
               input_tensor=None,  # 可选的keras张量，用作模型的图像输入
               input_shape=None,
               pooling=None,
               classes=1000,  # 用于分类图像的可选类数
               classifer_activation='softmax'):  # 分类层激活函数
    img_input = Input(shape=input_shape)
    x = ZeroPadding2D(padding=((3, 3), (3, 3)), name='conv1_pad')(img_input)
    x = Conv2D(64, 7, strides=2, use_bias=use_bias, name='conv1_conv')(x)
    
    if not preact:
        x = BatchNormalization(name='conv1_bn')(x)
        x = Activation('relu', name='conv1_relu')(x)
    
    x = ZeroPadding2D(padding=((1, 1), (1, 1)), name='pool1+pad')(x)
    x = MaxPooling2D(3, strides=2, name='pool1_pool')(x)
    
    x = stack2(x, 64, 3, name='conv2')
    x = stack2(x, 128, 4, name='conv3')
    x = stack2(x, 256, 6, name='conv4')
    x = stack2(x, 512, 3, strides=1, name='conv5')
    
    if preact:
        x = BatchNormalization(name='post_bn')(x)
        x = Activation('relu', name='post_relu')(x)
    if include_top:
        x = GlobalAveragePooling2D(name='avg_pool')(x)
        x = Dense(classes, activation=classifer_activation, name='predictions')(x)
    else:
        if pooling=='avg':
            # GlobalAveragePooling2D就是将每张图片的每个通道值各自加起来再求平均，
            # 最后结果是没有了宽高维度，只剩下个数与平均值两个维度
            # 可以理解成变成了多张单像素图片
            x = GlobalAveragePooling2D(name='avg_pool')(x)
        elif pooling=='max':
            x = GlobalMaxPooling2D(name='max_pool')(x)
    
    model = Model(img_input, x, name='resnet50v2')
    return model

Pytorch

''' 构建ResNet50V2 '''
class ResNet50V2(nn.Module):
    def __init__(self,
                 include_top=True,  # 是否包含位于网络顶部的全链接层
                 preact=True,  # 是否使用预激活
                 use_bias=True,  # 是否对卷积层使用偏置
                 input_shape=[224, 224, 3],
                 classes=1000,
                 pooling=None):  # 用于分类图像的可选类数
        super(ResNet50V2, self).__init__()
        
        self.conv1 = nn.Sequential()
        self.conv1.add_module('conv', nn.Conv2d(3, 64, 7, stride=2, padding=3, bias=use_bias, padding_mode='zeros'))
        if not preact:
            self.conv1.add_module('bn', nn.BatchNorm2d(64))
            self.conv1.add_module('relu', nn.ReLU())
        self.conv1.add_module('max_pool', nn.MaxPool2d(kernel_size=3, stride=2, padding=1))
        
        self.conv2 = Stack2(64, 64, 3)
        self.conv3 = Stack2(256, 128, 4)
        self.conv4 = Stack2(512, 256, 6)
        self.conv5 = Stack2(1024, 512, 3, stride=1)
        
        self.post = nn.Sequential()
        if preact:
            self.post.add_module('bn', nn.BatchNorm2d(2048))
            self.post.add_module('relu', nn.ReLU())
        if include_top:
            self.post.add_module('avg_pool', nn.AdaptiveAvgPool2d((1, 1)))
            self.post.add_module('flatten', nn.Flatten())
            self.post.add_module('fc', nn.Linear(2048, classes))
        else:
            if pooling=='avg':
                self.post.add_module('avg_pool', nn.AdaptiveAvgPool2d((1, 1)))
            elif pooling=='max':
                self.post.add_module('max_pool', nn.AdaptiveMaxPool2d((1, 1)))
    
    def forward(self, x):
        x = self.conv1(x)
        x = self.conv2(x)
        x = self.conv3(x)
        x = self.conv4(x)
        x = self.conv5(x)
        x = self.post(x)
        return x

网络结构打印

----------------------------------------------------------------
        Layer (type)               Output Shape         Param #
================================================================
            Conv2d-1         [-1, 64, 112, 112]           9,472
         MaxPool2d-2           [-1, 64, 56, 56]               0
       BatchNorm2d-3           [-1, 64, 56, 56]             128
              ReLU-4           [-1, 64, 56, 56]               0
            Conv2d-5          [-1, 256, 56, 56]          16,384
            Conv2d-6           [-1, 64, 56, 56]           4,096
       BatchNorm2d-7           [-1, 64, 56, 56]             128
              ReLU-8           [-1, 64, 56, 56]               0
            Conv2d-9           [-1, 64, 56, 56]          36,864
      BatchNorm2d-10           [-1, 64, 56, 56]             128
             ReLU-11           [-1, 64, 56, 56]               0
           Conv2d-12          [-1, 256, 56, 56]          16,384
           Block2-13          [-1, 256, 56, 56]               0
      BatchNorm2d-14          [-1, 256, 56, 56]             512
             ReLU-15          [-1, 256, 56, 56]               0
         Identity-16          [-1, 256, 56, 56]               0
           Conv2d-17           [-1, 64, 56, 56]          16,384
      BatchNorm2d-18           [-1, 64, 56, 56]             128
             ReLU-19           [-1, 64, 56, 56]               0
           Conv2d-20           [-1, 64, 56, 56]          36,864
      BatchNorm2d-21           [-1, 64, 56, 56]             128
             ReLU-22           [-1, 64, 56, 56]               0
           Conv2d-23          [-1, 256, 56, 56]          16,384
           Block2-24          [-1, 256, 56, 56]               0
      BatchNorm2d-25          [-1, 256, 56, 56]             512
             ReLU-26          [-1, 256, 56, 56]               0
        MaxPool2d-27          [-1, 256, 28, 28]               0
           Conv2d-28           [-1, 64, 56, 56]          16,384
      BatchNorm2d-29           [-1, 64, 56, 56]             128
             ReLU-30           [-1, 64, 56, 56]               0
           Conv2d-31           [-1, 64, 28, 28]          36,864
      BatchNorm2d-32           [-1, 64, 28, 28]             128
             ReLU-33           [-1, 64, 28, 28]               0
           Conv2d-34          [-1, 256, 28, 28]          16,384
           Block2-35          [-1, 256, 28, 28]               0
           Stack2-36          [-1, 256, 28, 28]               0
      BatchNorm2d-37          [-1, 256, 28, 28]             512
             ReLU-38          [-1, 256, 28, 28]               0
           Conv2d-39          [-1, 512, 28, 28]         131,072
           Conv2d-40          [-1, 128, 28, 28]          32,768
      BatchNorm2d-41          [-1, 128, 28, 28]             256
             ReLU-42          [-1, 128, 28, 28]               0
           Conv2d-43          [-1, 128, 28, 28]         147,456
      BatchNorm2d-44          [-1, 128, 28, 28]             256
             ReLU-45          [-1, 128, 28, 28]               0
           Conv2d-46          [-1, 512, 28, 28]          65,536
           Block2-47          [-1, 512, 28, 28]               0
      BatchNorm2d-48          [-1, 512, 28, 28]           1,024
             ReLU-49          [-1, 512, 28, 28]               0
         Identity-50          [-1, 512, 28, 28]               0
           Conv2d-51          [-1, 128, 28, 28]          65,536
      BatchNorm2d-52          [-1, 128, 28, 28]             256
             ReLU-53          [-1, 128, 28, 28]               0
           Conv2d-54          [-1, 128, 28, 28]         147,456
      BatchNorm2d-55          [-1, 128, 28, 28]             256
             ReLU-56          [-1, 128, 28, 28]               0
           Conv2d-57          [-1, 512, 28, 28]          65,536
           Block2-58          [-1, 512, 28, 28]               0
      BatchNorm2d-59          [-1, 512, 28, 28]           1,024
             ReLU-60          [-1, 512, 28, 28]               0
         Identity-61          [-1, 512, 28, 28]               0
           Conv2d-62          [-1, 128, 28, 28]          65,536
      BatchNorm2d-63          [-1, 128, 28, 28]             256
             ReLU-64          [-1, 128, 28, 28]               0
           Conv2d-65          [-1, 128, 28, 28]         147,456
      BatchNorm2d-66          [-1, 128, 28, 28]             256
             ReLU-67          [-1, 128, 28, 28]               0
           Conv2d-68          [-1, 512, 28, 28]          65,536
           Block2-69          [-1, 512, 28, 28]               0
      BatchNorm2d-70          [-1, 512, 28, 28]           1,024
             ReLU-71          [-1, 512, 28, 28]               0
        MaxPool2d-72          [-1, 512, 14, 14]               0
           Conv2d-73          [-1, 128, 28, 28]          65,536
      BatchNorm2d-74          [-1, 128, 28, 28]             256
             ReLU-75          [-1, 128, 28, 28]               0
           Conv2d-76          [-1, 128, 14, 14]         147,456
      BatchNorm2d-77          [-1, 128, 14, 14]             256
             ReLU-78          [-1, 128, 14, 14]               0
           Conv2d-79          [-1, 512, 14, 14]          65,536
           Block2-80          [-1, 512, 14, 14]               0
           Stack2-81          [-1, 512, 14, 14]               0
      BatchNorm2d-82          [-1, 512, 14, 14]           1,024
             ReLU-83          [-1, 512, 14, 14]               0
           Conv2d-84         [-1, 1024, 14, 14]         524,288
           Conv2d-85          [-1, 256, 14, 14]         131,072
      BatchNorm2d-86          [-1, 256, 14, 14]             512
             ReLU-87          [-1, 256, 14, 14]               0
           Conv2d-88          [-1, 256, 14, 14]         589,824
      BatchNorm2d-89          [-1, 256, 14, 14]             512
             ReLU-90          [-1, 256, 14, 14]               0
           Conv2d-91         [-1, 1024, 14, 14]         262,144
           Block2-92         [-1, 1024, 14, 14]               0
      BatchNorm2d-93         [-1, 1024, 14, 14]           2,048
             ReLU-94         [-1, 1024, 14, 14]               0
         Identity-95         [-1, 1024, 14, 14]               0
           Conv2d-96          [-1, 256, 14, 14]         262,144
      BatchNorm2d-97          [-1, 256, 14, 14]             512
             ReLU-98          [-1, 256, 14, 14]               0
           Conv2d-99          [-1, 256, 14, 14]         589,824
     BatchNorm2d-100          [-1, 256, 14, 14]             512
            ReLU-101          [-1, 256, 14, 14]               0
          Conv2d-102         [-1, 1024, 14, 14]         262,144
          Block2-103         [-1, 1024, 14, 14]               0
     BatchNorm2d-104         [-1, 1024, 14, 14]           2,048
            ReLU-105         [-1, 1024, 14, 14]               0
        Identity-106         [-1, 1024, 14, 14]               0
          Conv2d-107          [-1, 256, 14, 14]         262,144
     BatchNorm2d-108          [-1, 256, 14, 14]             512
            ReLU-109          [-1, 256, 14, 14]               0
          Conv2d-110          [-1, 256, 14, 14]         589,824
     BatchNorm2d-111          [-1, 256, 14, 14]             512
            ReLU-112          [-1, 256, 14, 14]               0
          Conv2d-113         [-1, 1024, 14, 14]         262,144
          Block2-114         [-1, 1024, 14, 14]               0
     BatchNorm2d-115         [-1, 1024, 14, 14]           2,048
            ReLU-116         [-1, 1024, 14, 14]               0
        Identity-117         [-1, 1024, 14, 14]               0
          Conv2d-118          [-1, 256, 14, 14]         262,144
     BatchNorm2d-119          [-1, 256, 14, 14]             512
            ReLU-120          [-1, 256, 14, 14]               0
          Conv2d-121          [-1, 256, 14, 14]         589,824
     BatchNorm2d-122          [-1, 256, 14, 14]             512
            ReLU-123          [-1, 256, 14, 14]               0
          Conv2d-124         [-1, 1024, 14, 14]         262,144
          Block2-125         [-1, 1024, 14, 14]               0
     BatchNorm2d-126         [-1, 1024, 14, 14]           2,048
            ReLU-127         [-1, 1024, 14, 14]               0
        Identity-128         [-1, 1024, 14, 14]               0
          Conv2d-129          [-1, 256, 14, 14]         262,144
     BatchNorm2d-130          [-1, 256, 14, 14]             512
            ReLU-131          [-1, 256, 14, 14]               0
          Conv2d-132          [-1, 256, 14, 14]         589,824
     BatchNorm2d-133          [-1, 256, 14, 14]             512
            ReLU-134          [-1, 256, 14, 14]               0
          Conv2d-135         [-1, 1024, 14, 14]         262,144
          Block2-136         [-1, 1024, 14, 14]               0
     BatchNorm2d-137         [-1, 1024, 14, 14]           2,048
            ReLU-138         [-1, 1024, 14, 14]               0
       MaxPool2d-139           [-1, 1024, 7, 7]               0
          Conv2d-140          [-1, 256, 14, 14]         262,144
     BatchNorm2d-141          [-1, 256, 14, 14]             512
            ReLU-142          [-1, 256, 14, 14]               0
          Conv2d-143            [-1, 256, 7, 7]         589,824
     BatchNorm2d-144            [-1, 256, 7, 7]             512
            ReLU-145            [-1, 256, 7, 7]               0
          Conv2d-146           [-1, 1024, 7, 7]         262,144
          Block2-147           [-1, 1024, 7, 7]               0
          Stack2-148           [-1, 1024, 7, 7]               0
     BatchNorm2d-149           [-1, 1024, 7, 7]           2,048
            ReLU-150           [-1, 1024, 7, 7]               0
          Conv2d-151           [-1, 2048, 7, 7]       2,097,152
          Conv2d-152            [-1, 512, 7, 7]         524,288
     BatchNorm2d-153            [-1, 512, 7, 7]           1,024
            ReLU-154            [-1, 512, 7, 7]               0
          Conv2d-155            [-1, 512, 7, 7]       2,359,296
     BatchNorm2d-156            [-1, 512, 7, 7]           1,024
            ReLU-157            [-1, 512, 7, 7]               0
          Conv2d-158           [-1, 2048, 7, 7]       1,048,576
          Block2-159           [-1, 2048, 7, 7]               0
     BatchNorm2d-160           [-1, 2048, 7, 7]           4,096
            ReLU-161           [-1, 2048, 7, 7]               0
        Identity-162           [-1, 2048, 7, 7]               0
          Conv2d-163            [-1, 512, 7, 7]       1,048,576
     BatchNorm2d-164            [-1, 512, 7, 7]           1,024
            ReLU-165            [-1, 512, 7, 7]               0
          Conv2d-166            [-1, 512, 7, 7]       2,359,296
     BatchNorm2d-167            [-1, 512, 7, 7]           1,024
            ReLU-168            [-1, 512, 7, 7]               0
          Conv2d-169           [-1, 2048, 7, 7]       1,048,576
          Block2-170           [-1, 2048, 7, 7]               0
     BatchNorm2d-171           [-1, 2048, 7, 7]           4,096
            ReLU-172           [-1, 2048, 7, 7]               0
        Identity-173           [-1, 2048, 7, 7]               0
          Conv2d-174            [-1, 512, 7, 7]       1,048,576
     BatchNorm2d-175            [-1, 512, 7, 7]           1,024
            ReLU-176            [-1, 512, 7, 7]               0
          Conv2d-177            [-1, 512, 7, 7]       2,359,296
     BatchNorm2d-178            [-1, 512, 7, 7]           1,024
            ReLU-179            [-1, 512, 7, 7]               0
          Conv2d-180           [-1, 2048, 7, 7]       1,048,576
          Block2-181           [-1, 2048, 7, 7]               0
          Stack2-182           [-1, 2048, 7, 7]               0
     BatchNorm2d-183           [-1, 2048, 7, 7]           4,096
            ReLU-184           [-1, 2048, 7, 7]               0
AdaptiveAvgPool2d-185           [-1, 2048, 1, 1]               0
         Flatten-186                 [-1, 2048]               0
          Linear-187                    [-1, 4]           8,196
================================================================
Total params: 23,508,612
Trainable params: 23,508,612
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.57
Forward/backward pass size (MB): 241.68
Params size (MB): 89.68
Estimated Total Size (MB): 331.93
----------------------------------------------------------------

ResNet50V2(
  (conv1): Sequential(
    (conv): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3))
    (max_pool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
  )
  (conv2): Stack2(
    (conv): Sequential(
      (0): Block2(
        (preact): Sequential(
          (0): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (1): ReLU(inplace=True)
        )
        (short): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (conv1): Sequential(
          (0): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): ReLU(inplace=True)
        )
        (conv2): Sequential(
          (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): ReLU(inplace=True)
        )
        (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
      )
      (1): Block2(
        (preact): Sequential(
          (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (1): ReLU(inplace=True)
        )
        (short): Identity()
        (conv1): Sequential(
          (0): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): ReLU(inplace=True)
        )
        (conv2): Sequential(
          (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): ReLU(inplace=True)
        )
        (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
      )
      (2): Block2(
        (preact): Sequential(
          (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (1): ReLU(inplace=True)
        )
        (short): MaxPool2d(kernel_size=1, stride=2, padding=0, dilation=1, ceil_mode=False)
        (conv1): Sequential(
          (0): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): ReLU(inplace=True)
        )
        (conv2): Sequential(
          (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
          (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): ReLU(inplace=True)
        )
        (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
      )
    )
  )
  (conv3): Stack2(
    (conv): Sequential(
      (0): Block2(
        (preact): Sequential(
          (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (1): ReLU(inplace=True)
        )
        (short): Conv2d(256, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (conv1): Sequential(
          (0): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): ReLU(inplace=True)
        )
        (conv2): Sequential(
          (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): ReLU(inplace=True)
        )
        (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
      )
      (1): Block2(
        (preact): Sequential(
          (0): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (1): ReLU(inplace=True)
        )
        (short): Identity()
        (conv1): Sequential(
          (0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): ReLU(inplace=True)
        )
        (conv2): Sequential(
          (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): ReLU(inplace=True)
        )
        (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
      )
      (2): Block2(
        (preact): Sequential(
          (0): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (1): ReLU(inplace=True)
        )
        (short): Identity()
        (conv1): Sequential(
          (0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): ReLU(inplace=True)
        )
        (conv2): Sequential(
          (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): ReLU(inplace=True)
        )
        (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
      )
      (3): Block2(
        (preact): Sequential(
          (0): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (1): ReLU(inplace=True)
        )
        (short): MaxPool2d(kernel_size=1, stride=2, padding=0, dilation=1, ceil_mode=False)
        (conv1): Sequential(
          (0): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): ReLU(inplace=True)
        )
        (conv2): Sequential(
          (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
          (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): ReLU(inplace=True)
        )
        (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
      )
    )
  )
  (conv4): Stack2(
    (conv): Sequential(
      (0): Block2(
        (preact): Sequential(
          (0): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (1): ReLU(inplace=True)
        )
        (short): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (conv1): Sequential(
          (0): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): ReLU(inplace=True)
        )
        (conv2): Sequential(
          (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): ReLU(inplace=True)
        )
        (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
      )
      (1): Block2(
        (preact): Sequential(
          (0): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (1): ReLU(inplace=True)
        )
        (short): Identity()
        (conv1): Sequential(
          (0): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): ReLU(inplace=True)
        )
        (conv2): Sequential(
          (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): ReLU(inplace=True)
        )
        (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
      )
      (2): Block2(
        (preact): Sequential(
          (0): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (1): ReLU(inplace=True)
        )
        (short): Identity()
        (conv1): Sequential(
          (0): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): ReLU(inplace=True)
        )
        (conv2): Sequential(
          (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): ReLU(inplace=True)
        )
        (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
      )
      (3): Block2(
        (preact): Sequential(
          (0): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (1): ReLU(inplace=True)
        )
        (short): Identity()
        (conv1): Sequential(
          (0): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): ReLU(inplace=True)
        )
        (conv2): Sequential(
          (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): ReLU(inplace=True)
        )
        (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
      )
      (4): Block2(
        (preact): Sequential(
          (0): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (1): ReLU(inplace=True)
        )
        (short): Identity()
        (conv1): Sequential(
          (0): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): ReLU(inplace=True)
        )
        (conv2): Sequential(
          (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): ReLU(inplace=True)
        )
        (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
      )
      (5): Block2(
        (preact): Sequential(
          (0): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (1): ReLU(inplace=True)
        )
        (short): MaxPool2d(kernel_size=1, stride=2, padding=0, dilation=1, ceil_mode=False)
        (conv1): Sequential(
          (0): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): ReLU(inplace=True)
        )
        (conv2): Sequential(
          (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
          (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): ReLU(inplace=True)
        )
        (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
      )
    )
  )
  (conv5): Stack2(
    (conv): Sequential(
      (0): Block2(
        (preact): Sequential(
          (0): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (1): ReLU(inplace=True)
        )
        (short): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (conv1): Sequential(
          (0): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): ReLU(inplace=True)
        )
        (conv2): Sequential(
          (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): ReLU(inplace=True)
        )
        (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
      )
      (1): Block2(
        (preact): Sequential(
          (0): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (1): ReLU(inplace=True)
        )
        (short): Identity()
        (conv1): Sequential(
          (0): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): ReLU(inplace=True)
        )
        (conv2): Sequential(
          (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): ReLU(inplace=True)
        )
        (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
      )
      (2): Block2(
        (preact): Sequential(
          (0): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (1): ReLU(inplace=True)
        )
        (short): Identity()
        (conv1): Sequential(
          (0): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): ReLU(inplace=True)
        )
        (conv2): Sequential(
          (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): ReLU(inplace=True)
        )
        (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
      )
    )
  )
  (post): Sequential(
    (bn): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    (relu): ReLU()
    (avg_pool): AdaptiveAvgPool2d(output_size=(1, 1))
    (flatten): Flatten(start_dim=1, end_dim=-1)
    (fc): Linear(in_features=2048, out_features=4, bias=True)
  )
)

运行结果

Start training...
[2023-02-16 16:13:40] Epoch: 1, Train_acc:21.2%, Train_loss:1.390, Test_acc:19.5%, Test_loss:1.403, Lr:1.00E-07
acc = 19.5%, saving model to best.pkl
[2023-02-16 16:13:52] Epoch: 2, Train_acc:21.7%, Train_loss:1.389, Test_acc:20.4%, Test_loss:1.419, Lr:1.00E-07
acc = 20.4%, saving model to best.pkl
[2023-02-16 16:14:03] Epoch: 3, Train_acc:22.1%, Train_loss:1.384, Test_acc:20.4%, Test_loss:1.412, Lr:1.00E-07
[2023-02-16 16:14:12] Epoch: 4, Train_acc:22.1%, Train_loss:1.386, Test_acc:18.6%, Test_loss:1.398, Lr:1.00E-07
[2023-02-16 16:14:23] Epoch: 5, Train_acc:22.6%, Train_loss:1.384, Test_acc:21.2%, Test_loss:1.407, Lr:1.00E-07
acc = 21.2%, saving model to best.pkl
[2023-02-16 16:14:34] Epoch: 6, Train_acc:25.7%, Train_loss:1.381, Test_acc:17.7%, Test_loss:1.412, Lr:1.00E-07
[2023-02-16 16:14:44] Epoch: 7, Train_acc:23.7%, Train_loss:1.381, Test_acc:18.6%, Test_loss:1.395, Lr:1.00E-07
[2023-02-16 16:14:55] Epoch: 8, Train_acc:25.7%, Train_loss:1.375, Test_acc:16.8%, Test_loss:1.400, Lr:1.00E-07
[2023-02-16 16:15:06] Epoch: 9, Train_acc:24.3%, Train_loss:1.379, Test_acc:21.2%, Test_loss:1.394, Lr:1.00E-07
[2023-02-16 16:15:16] Epoch:10, Train_acc:25.9%, Train_loss:1.376, Test_acc:23.0%, Test_loss:1.411, Lr:1.00E-07
acc = 23.0%, saving model to best.pkl
Done

EVAL 0.23009, 1.41133

4.ResNet50V2模型结构大图

在这里插入图片描述

Oaix Nay
关注
专栏目录
目标检测YOLO实战应用案例100讲-基于改进的YOLOv4柑橘目标检测算法
qq_36130719的博客
06-21 1186
上世纪60年代，计算机视觉[1]（Computer Vision，CV）的概念被提出并定义为简单几何物体的形状识别和重建。随着科技的进步，计算机技术渗透到人们生活的方方面面。计算机视觉技术赋予计算机以人类智慧，计算机依靠“眼睛”观察世界、通过“大脑”处理信息和认识世界——摄像头获取外界的图像或视频，特征提取器获得位置信息和语义信息。人类的想象力只能到达三维空间，计算机却可以轻松处理一些高维的、抽象的信息，能够参与到诸如视频分析、图像识别等复杂任务中，人们的工作和生活被大大简化。
目标检测YOLO实战应用案例100讲-联合深度图聚类与目标检测的语义SLAM算法研究
qq_36130719的博客
06-17 1512
目标检测的研究可以追溯到20世纪90年代[18]，2014年R-CNN[1]的提出标志着目标检测从传统手工特征时代进入到深度学习时代。2014年之前可以称为传统目标检测时代，其最具代表性的方法有VJ检测器[19]、HOG检测器[20]、DPM检测器[21]。它们有着共同的特点就是使用手工设计的特征描述子如方向梯度直方图[20]（Histogramof Oriented Gradient，HOG）来提取图像特征，使用机器学习方法如SVM或AdaBoost分类器来分类目标。
resnet50-v2-7.onnx
10-24
resnet50 的onnx文件
ResNet50V2
最新发布
weixin_53657683的博客
07-03 838
ResNetV2和ResNetV1都是深度残差网络（ResNet）的变体，它们的主要区别在于残差块的设计和批归一化（Batch Normalization, BN）的使用方式。ResNetV2是在ResNetV1的基础上进行改进的一种版本，旨在提高模型的性能和稳定性。在ResNetV1中，批归一化层位于每个卷积层的后面，ReLU 激活函数在批归一化之后。在ResNetV2中，批归一化和 ReLU 激活函数在每个卷积层之前进行。这种改变使得信息在模型中传播得更加顺畅，减轻了梯度消失的问题。
ResNet50V2 网络结构
NLP与推荐算法
11-15 3033
来源于官方函数，input_shape=[160,160,3],classes=16 Layer (type) Output Shape Param # Connected to ========================================================...
深度学习第J2周：ResNet50V2算法实战与解析
m0_62237233的博客
03-19 2157
何恺明大神在这篇论文中提出了一种新的残差单元。我们将这篇论文中的ResNet结构称为ResNetV2。
第J2周：ResNet50V2算法实战与解析
Pinospot的博客
02-17 482
ResNet50V2算法实战与解析
经典CNN算法解析实战-第J5周：DenseNet+SE-Net实战
Oaix的博客
03-10 1317
DenseNet+SE-Net实战
经典CNN算法解析实战-第J6周：ResNeXt-50实战解析
Oaix的博客
03-17 548
第J6周：ResNeXt-50实战解析
每周论文精读05-A2J:AnchortoJointRegressionNetwork for 3D ArticulatedPoseEstimation from a SingleDepthImage
Jason_____Wang的博客
04-08 1652
https://download.csdn.net/download/Jason_____Wang/16502249 论文精读——A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation from a Single Depth Image 标题比较长，已经打不完了。。 所以题目格式有些变形，望谅解。 上周尝试做了一下代码复现的方向，因为生活琐碎以及清明假期，文献精读的工作有所耽误，本周继续做文献精读工作，初步选取的目
残差网络resnet_50_ckpt文件
06-10
resnet50已训练好模型参数，可在自己的数据上进行微调。tensorflow
pytorch-deeplab-resnet：pytorch中的DeepLab resnet v2模型
02-05
pytorch-deeplab-resnet 模型实现。 deepLab-ResNet的体系结构已完全复制自caffe实现。 该体系结构可在多个比例（1x，0.75x，0.5x）上计算输入图像上的损耗。 在这三个等级上分别计算损失。 除了这3个损失外，在将3个标度上的输出得分图合并后，还会计算出一个损失。 将这4个损失相加以计算总损失。 更新 2017年7月18日 添加了另一个评估脚本evalpyt2.py 。 旧的评价脚本evalpyt.py使用不同的methodoloy拿白条平均比所使用的一个。 结果部分已更新，以纳入此更改。 2017年6月24日 现在，与caffe实现一样，可以共
Microsoft.ML.OnnxRuntime.ResNet50v2Sample.7z
07-19
Microsoft.ML.OnnxRuntime.ResNet50v2Sample.7z
365天深度学习训练营-第J2周：ResNet50V2算法实战与解析
m0_58585940的博客
02-17 1403
要求：1.根据本文的Tensorflow代码，编写Pytorch代码2.了解ResnetV2和Resnet的区别3.改进地方可以迁移到哪里呢。
深度学习-第J2周：ResNet-50-V2算法
weixin_43397208的博客
07-01 640
上周复现了何恺明在2015年提出的深度残差网络ResNet（deep residual network），大神在后来的论文中提到一种全新的残差单元，我们命名为ResNet_V2, 本文将在上周的基础上基于Pytorch实现ResNet_V2模型深度学习-第J1周：ResNet-50算法的Pytorch实现及解析_quant_day的博客-CSDN博客。
J2resnet50v2
tjl521314_21的博客
03-20 694
前面对resnet有了一定了解，主要关注其残差结构，其缓解了梯度消失的问题，是卷积神经网络的一大创举，这周主要学习resnet50v2,其是对resnet的改进。ResNet50V2 是对 ResNet50 的改进版本，它在保留了 ResNet 架构的基本特征的同时，进行了一些改动和优化，以提升模型性能和训练效率。
深度学习训练营J2:ResNet50v2算法分析与实战
qq_62904883的博客
05-12 863
主要看了ResNet50v2的论文,感觉学到了不少内容
基于tensorflow的ResNet50V2网络识别动物
11-29 2177
之前很多人在，如何进行XXX的识别，对应的神经网络如何搭建。对应神经网络怎么搭建，我也是照本宣科，只能说看得懂而已，没有对这块进行深入的研究，但是现在tensorflow，paddle这些工具，都提供了非常成熟的神经网络进行直接使用。本文对过往的一些文章进行改造，使用已经集成的神经网络，简单的实现多个种类的动物识别。
评论
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值