【tensorflow2.0】27.tf2.0实现ResNet

最新推荐文章于 2021-10-20 20:31:27 发布
最新推荐文章于 2021-10-20 20:31:27 发布
阅读量764 收藏 4
点赞数 1
分类专栏： tensorflow2.0学习笔记 文章标签： 神经网络 tensorflow
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/weixin_39122088/article/details/106938696
版权

    终于到ResNet了，这个模型的复现比前边的网络难度要大不少，因为前边的都属顺序网络，一层接一层，而ResNet引入了残差结构。它差不多是当前应用最为广泛的CNN特征提取网络。它的提出始于2015年，作者中间有大名鼎鼎的三位人物He-Kaiming, Ren-Shaoqing, Sun-Jian。Resnet是残差网络(Residual Network)的缩写,该系列网络广泛用于目标分类等领域以及作为计算机视觉任务主干经典神经网络的一部分，典型的网络有resnet50, resnet101等。Resnet网络的证明网络能够向更深（包含更多隐藏层）的方向发展。

    ResNet50有两个基本的块，分别名为Conv Block和Identity Block，其中Conv Block输入和输出的维度是不一样的，所以不能连续串联，它的作用是改变网络的维度；Identity Block输入维度和输出维度相同，可以串联，用于加深网络的。

Conv Block的结构如下(图片以及代码来源)：
在这里插入图片描述
Identity Block的结构如下：
在这里插入图片描述
总的网络结构如下：
在这里插入图片描述
我们可以发现，出了这两个残差结构以外，都是我们熟悉的结构，所以我们可以先将这两个残差结构写出来。

#第一个结构快
def conv_block(input_tensor, kernel_size, filters, stage, block, strides=(2, 2)):

    filters1, filters2, filters3 = filters

    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'

    x = Conv2D(filters1, (1, 1), strides=strides,
               name=conv_name_base + '2a')(input_tensor)
    x = BatchNormalization(name=bn_name_base + '2a')(x)
    x = Activation('relu')(x)

    x = Conv2D(filters2, kernel_size, padding='same',
               name=conv_name_base + '2b')(x)
    x = BatchNormalization(name=bn_name_base + '2b')(x)
    x = Activation('relu')(x)

    x = Conv2D(filters3, (1, 1), name=conv_name_base + '2c')(x)
    x = BatchNormalization(name=bn_name_base + '2c')(x)

    shortcut = Conv2D(filters3, (1, 1), strides=strides,
                      name=conv_name_base + '1')(input_tensor)
    shortcut = BatchNormalization(name=bn_name_base + '1')(shortcut)

    x = layers.add([x, shortcut])
    x = Activation('relu')(x)
    return x

#第二个

def identity_block(input_tensor, kernel_size, filters, stage, block):

    filters1, filters2, filters3 = filters

    conv_name_base = 'res' + str(stage) + block + '_branch'
    bn_name_base = 'bn' + str(stage) + block + '_branch'

    x = Conv2D(filters1, (1, 1), name=conv_name_base + '2a')(input_tensor)
    x = BatchNormalization(name=bn_name_base + '2a')(x)
    x = Activation('relu')(x)

    x = Conv2D(filters2, kernel_size,padding='same', name=conv_name_base + '2b')(x)

    x = BatchNormalization(name=bn_name_base + '2b')(x)
    x = Activation('relu')(x)

    x = Conv2D(filters3, (1, 1), name=conv_name_base + '2c')(x)
    x = BatchNormalization(name=bn_name_base + '2c')(x)

    x = layers.add([x, input_tensor])
    x = Activation('relu')(x)
    return x

接下来就是残差网络：

inputs = tf.keras.Input([224,224,3])
x = ZeroPadding2D((3, 3))(inputs)

x = Conv2D(64, (7, 7), strides=(2, 2), name='conv1')(x)
x = BatchNormalization(name='bn_conv1')(x)
x = Activation('relu')(x)
x = MaxPooling2D((3, 3), strides=(2, 2))(x)

x = conv_block(x, 3, [64, 64, 256], stage=2, block='a', strides=(1, 1))
x = identity_block(x, 3, [64, 64, 256], stage=2, block='b')
x = identity_block(x, 3, [64, 64, 256], stage=2, block='c')

x = conv_block(x, 3, [128, 128, 512], stage=3, block='a')
x = identity_block(x, 3, [128, 128, 512], stage=3, block='b')
x = identity_block(x, 3, [128, 128, 512], stage=3, block='c')
x = identity_block(x, 3, [128, 128, 512], stage=3, block='d')

x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='b')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='c')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='d')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='e')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='f')

x = conv_block(x, 3, [512, 512, 2048], stage=5, block='a')
x = identity_block(x, 3, [512, 512, 2048], stage=5, block='b')
x = identity_block(x, 3, [512, 512, 2048], stage=5, block='c')

x = AveragePooling2D((7, 7), name='avg_pool')(x)

x = Flatten()(x)
x = Dense(1000, activation='softmax', name='fc1000')(x)
model = tf.keras.Model(inputs,x)
model.summary()

Model: "model"
__________________________________________________________________________________________________
Layer (type)                    Output Shape         Param #     Connected to                     
==================================================================================================
input_2 (InputLayer)            [(None, 224, 224, 3) 0                                            
__________________________________________________________________________________________________
zero_padding2d_7 (ZeroPadding2D (None, 230, 230, 3)  0           input_2[0][0]                    
__________________________________________________________________________________________________
conv1 (Conv2D)                  (None, 112, 112, 64) 9472        zero_padding2d_7[0][0]           
__________________________________________________________________________________________________
bn_conv1 (BatchNormalization)   (None, 112, 112, 64) 256         conv1[0][0]                      
__________________________________________________________________________________________________
activation_103 (Activation)     (None, 112, 112, 64) 0           bn_conv1[0][0]                   
__________________________________________________________________________________________________
max_pooling2d_5 (MaxPooling2D)  (None, 55, 55, 64)   0           activation_103[0][0]             
__________________________________________________________________________________________________
res2a_branch2a (Conv2D)         (None, 55, 55, 64)   4160        max_pooling2d_5[0][0]            
__________________________________________________________________________________________________
bn2a_branch2a (BatchNormalizati (None, 55, 55, 64)   256         res2a_branch2a[0][0]             
__________________________________________________________________________________________________
activation_104 (Activation)     (None, 55, 55, 64)   0           bn2a_branch2a[0][0]              
__________________________________________________________________________________________________
res2a_branch2b (Conv2D)         (None, 55, 55, 64)   36928       activation_104[0][0]             
__________________________________________________________________________________________________
bn2a_branch2b (BatchNormalizati (None, 55, 55, 64)   256         res2a_branch2b[0][0]             
__________________________________________________________________________________________________
activation_105 (Activation)     (None, 55, 55, 64)   0           bn2a_branch2b[0][0]              
__________________________________________________________________________________________________
res2a_branch2c (Conv2D)         (None, 55, 55, 256)  16640       activation_105[0][0]             
__________________________________________________________________________________________________
res2a_branch1 (Conv2D)          (None, 55, 55, 256)  16640       max_pooling2d_5[0][0]            
__________________________________________________________________________________________________
bn2a_branch2c (BatchNormalizati (None, 55, 55, 256)  1024        res2a_branch2c[0][0]             
__________________________________________________________________________________________________
bn2a_branch1 (BatchNormalizatio (None, 55, 55, 256)  1024        res2a_branch1[0][0]              
__________________________________________________________________________________________________
add_32 (Add)                    (None, 55, 55, 256)  0           bn2a_branch2c[0][0]              
                                                                 bn2a_branch1[0][0]               
__________________________________________________________________________________________________
activation_106 (Activation)     (None, 55, 55, 256)  0           add_32[0][0]                     
__________________________________________________________________________________________________
res2b_branch2a (Conv2D)         (None, 55, 55, 64)   16448       activation_106[0][0]             
__________________________________________________________________________________________________
bn2b_branch2a (BatchNormalizati (None, 55, 55, 64)   256         res2b_branch2a[0][0]             
__________________________________________________________________________________________________
activation_107 (Activation)     (None, 55, 55, 64)   0           bn2b_branch2a[0][0]              
__________________________________________________________________________________________________
res2b_branch2b (Conv2D)         (None, 55, 55, 64)   36928       activation_107[0][0]             
__________________________________________________________________________________________________
bn2b_branch2b (BatchNormalizati (None, 55, 55, 64)   256         res2b_branch2b[0][0]             
__________________________________________________________________________________________________
activation_108 (Activation)     (None, 55, 55, 64)   0           bn2b_branch2b[0][0]              
__________________________________________________________________________________________________
res2b_branch2c (Conv2D)         (None, 55, 55, 256)  16640       activation_108[0][0]             
__________________________________________________________________________________________________
bn2b_branch2c (BatchNormalizati (None, 55, 55, 256)  1024        res2b_branch2c[0][0]             
__________________________________________________________________________________________________
add_33 (Add)                    (None, 55, 55, 256)  0           bn2b_branch2c[0][0]              
                                                                 activation_106[0][0]             
__________________________________________________________________________________________________
activation_109 (Activation)     (None, 55, 55, 256)  0           add_33[0][0]                     
__________________________________________________________________________________________________
res2c_branch2a (Conv2D)         (None, 55, 55, 64)   16448       activation_109[0][0]             
__________________________________________________________________________________________________
bn2c_branch2a (BatchNormalizati (None, 55, 55, 64)   256         res2c_branch2a[0][0]             
__________________________________________________________________________________________________
activation_110 (Activation)     (None, 55, 55, 64)   0           bn2c_branch2a[0][0]              
__________________________________________________________________________________________________
res2c_branch2b (Conv2D)         (None, 55, 55, 64)   36928       activation_110[0][0]             
__________________________________________________________________________________________________
bn2c_branch2b (BatchNormalizati (None, 55, 55, 64)   256         res2c_branch2b[0][0]             
__________________________________________________________________________________________________
activation_111 (Activation)     (None, 55, 55, 64)   0           bn2c_branch2b[0][0]              
__________________________________________________________________________________________________
res2c_branch2c (Conv2D)         (None, 55, 55, 256)  16640       activation_111[0][0]             
__________________________________________________________________________________________________
bn2c_branch2c (BatchNormalizati (None, 55, 55, 256)  1024        res2c_branch2c[0][0]             
__________________________________________________________________________________________________
add_34 (Add)                    (None, 55, 55, 256)  0           bn2c_branch2c[0][0]              
                                                                 activation_109[0][0]             
__________________________________________________________________________________________________
activation_112 (Activation)     (None, 55, 55, 256)  0           add_34[0][0]                     
__________________________________________________________________________________________________
res3a_branch2a (Conv2D)         (None, 28, 28, 128)  32896       activation_112[0][0]             
__________________________________________________________________________________________________
bn3a_branch2a (BatchNormalizati (None, 28, 28, 128)  512         res3a_branch2a[0][0]             
__________________________________________________________________________________________________
activation_113 (Activation)     (None, 28, 28, 128)  0           bn3a_branch2a[0][0]              
__________________________________________________________________________________________________
res3a_branch2b (Conv2D)         (None, 28, 28, 128)  147584      activation_113[0][0]             
__________________________________________________________________________________________________
bn3a_branch2b (BatchNormalizati (None, 28, 28, 128)  512         res3a_branch2b[0][0]             
__________________________________________________________________________________________________
activation_114 (Activation)     (None, 28, 28, 128)  0           bn3a_branch2b[0][0]              
__________________________________________________________________________________________________
res3a_branch2c (Conv2D)         (None, 28, 28, 512)  66048       activation_114[0][0]             
__________________________________________________________________________________________________
res3a_branch1 (Conv2D)          (None, 28, 28, 512)  131584      activation_112[0][0]             
__________________________________________________________________________________________________
bn3a_branch2c (BatchNormalizati (None, 28, 28, 512)  2048        res3a_branch2c[0][0]             
__________________________________________________________________________________________________
bn3a_branch1 (BatchNormalizatio (None, 28, 28, 512)  2048        res3a_branch1[0][0]              
__________________________________________________________________________________________________
add_35 (Add)                    (None, 28, 28, 512)  0           bn3a_branch2c[0][0]              
                                                                 bn3a_branch1[0][0]               
__________________________________________________________________________________________________
activation_115 (Activation)     (None, 28, 28, 512)  0           add_35[0][0]                     
__________________________________________________________________________________________________
res3b_branch2a (Conv2D)         (None, 28, 28, 128)  65664       activation_115[0][0]             
__________________________________________________________________________________________________
bn3b_branch2a (BatchNormalizati (None, 28, 28, 128)  512         res3b_branch2a[0][0]             
__________________________________________________________________________________________________
activation_116 (Activation)     (None, 28, 28, 128)  0           bn3b_branch2a[0][0]              
__________________________________________________________________________________________________
res3b_branch2b (Conv2D)         (None, 28, 28, 128)  147584      activation_116[0][0]             
__________________________________________________________________________________________________
bn3b_branch2b (BatchNormalizati (None, 28, 28, 128)  512         res3b_branch2b[0][0]             
__________________________________________________________________________________________________
activation_117 (Activation)     (None, 28, 28, 128)  0           bn3b_branch2b[0][0]              
__________________________________________________________________________________________________
res3b_branch2c (Conv2D)         (None, 28, 28, 512)  66048       activation_117[0][0]             
__________________________________________________________________________________________________
bn3b_branch2c (BatchNormalizati (None, 28, 28, 512)  2048        res3b_branch2c[0][0]             
__________________________________________________________________________________________________
add_36 (Add)                    (None, 28, 28, 512)  0           bn3b_branch2c[0][0]              
                                                                 activation_115[0][0]             
__________________________________________________________________________________________________
activation_118 (Activation)     (None, 28, 28, 512)  0           add_36[0][0]                     
__________________________________________________________________________________________________
res3c_branch2a (Conv2D)         (None, 28, 28, 128)  65664       activation_118[0][0]             
__________________________________________________________________________________________________
bn3c_branch2a (BatchNormalizati (None, 28, 28, 128)  512         res3c_branch2a[0][0]             
__________________________________________________________________________________________________
activation_119 (Activation)     (None, 28, 28, 128)  0           bn3c_branch2a[0][0]              
__________________________________________________________________________________________________
res3c_branch2b (Conv2D)         (None, 28, 28, 128)  147584      activation_119[0][0]             
__________________________________________________________________________________________________
bn3c_branch2b (BatchNormalizati (None, 28, 28, 128)  512         res3c_branch2b[0][0]             
__________________________________________________________________________________________________
activation_120 (Activation)     (None, 28, 28, 128)  0           bn3c_branch2b[0][0]              
__________________________________________________________________________________________________
res3c_branch2c (Conv2D)         (None, 28, 28, 512)  66048       activation_120[0][0]             
__________________________________________________________________________________________________
bn3c_branch2c (BatchNormalizati (None, 28, 28, 512)  2048        res3c_branch2c[0][0]             
__________________________________________________________________________________________________
add_37 (Add)                    (None, 28, 28, 512)  0           bn3c_branch2c[0][0]              
                                                                 activation_118[0][0]             
__________________________________________________________________________________________________
activation_121 (Activation)     (None, 28, 28, 512)  0           add_37[0][0]                     
__________________________________________________________________________________________________
res3d_branch2a (Conv2D)         (None, 28, 28, 128)  65664       activation_121[0][0]             
__________________________________________________________________________________________________
bn3d_branch2a (BatchNormalizati (None, 28, 28, 128)  512         res3d_branch2a[0][0]             
__________________________________________________________________________________________________
activation_122 (Activation)     (None, 28, 28, 128)  0           bn3d_branch2a[0][0]              
__________________________________________________________________________________________________
res3d_branch2b (Conv2D)         (None, 28, 28, 128)  147584      activation_122[0][0]             
__________________________________________________________________________________________________
bn3d_branch2b (BatchNormalizati (None, 28, 28, 128)  512         res3d_branch2b[0][0]             
__________________________________________________________________________________________________
activation_123 (Activation)     (None, 28, 28, 128)  0           bn3d_branch2b[0][0]              
__________________________________________________________________________________________________
res3d_branch2c (Conv2D)         (None, 28, 28, 512)  66048       activation_123[0][0]             
__________________________________________________________________________________________________
bn3d_branch2c (BatchNormalizati (None, 28, 28, 512)  2048        res3d_branch2c[0][0]             
__________________________________________________________________________________________________
add_38 (Add)                    (None, 28, 28, 512)  0           bn3d_branch2c[0][0]              
                                                                 activation_121[0][0]             
__________________________________________________________________________________________________
activation_124 (Activation)     (None, 28, 28, 512)  0           add_38[0][0]                     
__________________________________________________________________________________________________
res4a_branch2a (Conv2D)         (None, 14, 14, 256)  131328      activation_124[0][0]             
__________________________________________________________________________________________________
bn4a_branch2a (BatchNormalizati (None, 14, 14, 256)  1024        res4a_branch2a[0][0]             
__________________________________________________________________________________________________
activation_125 (Activation)     (None, 14, 14, 256)  0           bn4a_branch2a[0][0]              
__________________________________________________________________________________________________
res4a_branch2b (Conv2D)         (None, 14, 14, 256)  590080      activation_125[0][0]             
__________________________________________________________________________________________________
bn4a_branch2b (BatchNormalizati (None, 14, 14, 256)  1024        res4a_branch2b[0][0]             
__________________________________________________________________________________________________
activation_126 (Activation)     (None, 14, 14, 256)  0           bn4a_branch2b[0][0]              
__________________________________________________________________________________________________
res4a_branch2c (Conv2D)         (None, 14, 14, 1024) 263168      activation_126[0][0]             
__________________________________________________________________________________________________
res4a_branch1 (Conv2D)          (None, 14, 14, 1024) 525312      activation_124[0][0]             
__________________________________________________________________________________________________
bn4a_branch2c (BatchNormalizati (None, 14, 14, 1024) 4096        res4a_branch2c[0][0]             
__________________________________________________________________________________________________
bn4a_branch1 (BatchNormalizatio (None, 14, 14, 1024) 4096        res4a_branch1[0][0]              
__________________________________________________________________________________________________
add_39 (Add)                    (None, 14, 14, 1024) 0           bn4a_branch2c[0][0]              
                                                                 bn4a_branch1[0][0]               
__________________________________________________________________________________________________
activation_127 (Activation)     (None, 14, 14, 1024) 0           add_39[0][0]                     
__________________________________________________________________________________________________
res4b_branch2a (Conv2D)         (None, 14, 14, 256)  262400      activation_127[0][0]             
__________________________________________________________________________________________________
bn4b_branch2a (BatchNormalizati (None, 14, 14, 256)  1024        res4b_branch2a[0][0]             
__________________________________________________________________________________________________
activation_128 (Activation)     (None, 14, 14, 256)  0           bn4b_branch2a[0][0]              
__________________________________________________________________________________________________
res4b_branch2b (Conv2D)         (None, 14, 14, 256)  590080      activation_128[0][0]             
__________________________________________________________________________________________________
bn4b_branch2b (BatchNormalizati (None, 14, 14, 256)  1024        res4b_branch2b[0][0]             
__________________________________________________________________________________________________
activation_129 (Activation)     (None, 14, 14, 256)  0           bn4b_branch2b[0][0]              
__________________________________________________________________________________________________
res4b_branch2c (Conv2D)         (None, 14, 14, 1024) 263168      activation_129[0][0]             
__________________________________________________________________________________________________
bn4b_branch2c (BatchNormalizati (None, 14, 14, 1024) 4096        res4b_branch2c[0][0]             
__________________________________________________________________________________________________
add_40 (Add)                    (None, 14, 14, 1024) 0           bn4b_branch2c[0][0]              
                                                                 activation_127[0][0]             
__________________________________________________________________________________________________
activation_130 (Activation)     (None, 14, 14, 1024) 0           add_40[0][0]                     
__________________________________________________________________________________________________
res4c_branch2a (Conv2D)         (None, 14, 14, 256)  262400      activation_130[0][0]             
__________________________________________________________________________________________________
bn4c_branch2a (BatchNormalizati (None, 14, 14, 256)  1024        res4c_branch2a[0][0]             
__________________________________________________________________________________________________
activation_131 (Activation)     (None, 14, 14, 256)  0           bn4c_branch2a[0][0]              
__________________________________________________________________________________________________
res4c_branch2b (Conv2D)         (None, 14, 14, 256)  590080      activation_131[0][0]             
__________________________________________________________________________________________________
bn4c_branch2b (BatchNormalizati (None, 14, 14, 256)  1024        res4c_branch2b[0][0]             
__________________________________________________________________________________________________
activation_132 (Activation)     (None, 14, 14, 256)  0           bn4c_branch2b[0][0]              
__________________________________________________________________________________________________
res4c_branch2c (Conv2D)         (None, 14, 14, 1024) 263168      activation_132[0][0]             
__________________________________________________________________________________________________
bn4c_branch2c (BatchNormalizati (None, 14, 14, 1024) 4096        res4c_branch2c[0][0]             
__________________________________________________________________________________________________
add_41 (Add)                    (None, 14, 14, 1024) 0           bn4c_branch2c[0][0]              
                                                                 activation_130[0][0]             
__________________________________________________________________________________________________
activation_133 (Activation)     (None, 14, 14, 1024) 0           add_41[0][0]                     
__________________________________________________________________________________________________
res4d_branch2a (Conv2D)         (None, 14, 14, 256)  262400      activation_133[0][0]             
__________________________________________________________________________________________________
bn4d_branch2a (BatchNormalizati (None, 14, 14, 256)  1024        res4d_branch2a[0][0]             
__________________________________________________________________________________________________
activation_134 (Activation)     (None, 14, 14, 256)  0           bn4d_branch2a[0][0]              
__________________________________________________________________________________________________
res4d_branch2b (Conv2D)         (None, 14, 14, 256)  590080      activation_134[0][0]             
__________________________________________________________________________________________________
bn4d_branch2b (BatchNormalizati (None, 14, 14, 256)  1024        res4d_branch2b[0][0]             
__________________________________________________________________________________________________
activation_135 (Activation)     (None, 14, 14, 256)  0           bn4d_branch2b[0][0]              
__________________________________________________________________________________________________
res4d_branch2c (Conv2D)         (None, 14, 14, 1024) 263168      activation_135[0][0]             
__________________________________________________________________________________________________
bn4d_branch2c (BatchNormalizati (None, 14, 14, 1024) 4096        res4d_branch2c[0][0]             
__________________________________________________________________________________________________
add_42 (Add)                    (None, 14, 14, 1024) 0           bn4d_branch2c[0][0]              
                                                                 activation_133[0][0]             
__________________________________________________________________________________________________
activation_136 (Activation)     (None, 14, 14, 1024) 0           add_42[0][0]                     
__________________________________________________________________________________________________
res4e_branch2a (Conv2D)         (None, 14, 14, 256)  262400      activation_136[0][0]             
__________________________________________________________________________________________________
bn4e_branch2a (BatchNormalizati (None, 14, 14, 256)  1024        res4e_branch2a[0][0]             
__________________________________________________________________________________________________
activation_137 (Activation)     (None, 14, 14, 256)  0           bn4e_branch2a[0][0]              
__________________________________________________________________________________________________
res4e_branch2b (Conv2D)         (None, 14, 14, 256)  590080      activation_137[0][0]             
__________________________________________________________________________________________________
bn4e_branch2b (BatchNormalizati (None, 14, 14, 256)  1024        res4e_branch2b[0][0]             
__________________________________________________________________________________________________
activation_138 (Activation)     (None, 14, 14, 256)  0           bn4e_branch2b[0][0]              
__________________________________________________________________________________________________
res4e_branch2c (Conv2D)         (None, 14, 14, 1024) 263168      activation_138[0][0]             
__________________________________________________________________________________________________
bn4e_branch2c (BatchNormalizati (None, 14, 14, 1024) 4096        res4e_branch2c[0][0]             
__________________________________________________________________________________________________
add_43 (Add)                    (None, 14, 14, 1024) 0           bn4e_branch2c[0][0]              
                                                                 activation_136[0][0]             
__________________________________________________________________________________________________
activation_139 (Activation)     (None, 14, 14, 1024) 0           add_43[0][0]                     
__________________________________________________________________________________________________
res4f_branch2a (Conv2D)         (None, 14, 14, 256)  262400      activation_139[0][0]             
__________________________________________________________________________________________________
bn4f_branch2a (BatchNormalizati (None, 14, 14, 256)  1024        res4f_branch2a[0][0]             
__________________________________________________________________________________________________
activation_140 (Activation)     (None, 14, 14, 256)  0           bn4f_branch2a[0][0]              
__________________________________________________________________________________________________
res4f_branch2b (Conv2D)         (None, 14, 14, 256)  590080      activation_140[0][0]             
__________________________________________________________________________________________________
bn4f_branch2b (BatchNormalizati (None, 14, 14, 256)  1024        res4f_branch2b[0][0]             
__________________________________________________________________________________________________
activation_141 (Activation)     (None, 14, 14, 256)  0           bn4f_branch2b[0][0]              
__________________________________________________________________________________________________
res4f_branch2c (Conv2D)         (None, 14, 14, 1024) 263168      activation_141[0][0]             
__________________________________________________________________________________________________
bn4f_branch2c (BatchNormalizati (None, 14, 14, 1024) 4096        res4f_branch2c[0][0]             
__________________________________________________________________________________________________
add_44 (Add)                    (None, 14, 14, 1024) 0           bn4f_branch2c[0][0]              
                                                                 activation_139[0][0]             
__________________________________________________________________________________________________
activation_142 (Activation)     (None, 14, 14, 1024) 0           add_44[0][0]                     
__________________________________________________________________________________________________
res5a_branch2a (Conv2D)         (None, 7, 7, 512)    524800      activation_142[0][0]             
__________________________________________________________________________________________________
bn5a_branch2a (BatchNormalizati (None, 7, 7, 512)    2048        res5a_branch2a[0][0]             
__________________________________________________________________________________________________
activation_143 (Activation)     (None, 7, 7, 512)    0           bn5a_branch2a[0][0]              
__________________________________________________________________________________________________
res5a_branch2b (Conv2D)         (None, 7, 7, 512)    2359808     activation_143[0][0]             
__________________________________________________________________________________________________
bn5a_branch2b (BatchNormalizati (None, 7, 7, 512)    2048        res5a_branch2b[0][0]             
__________________________________________________________________________________________________
activation_144 (Activation)     (None, 7, 7, 512)    0           bn5a_branch2b[0][0]              
__________________________________________________________________________________________________
res5a_branch2c (Conv2D)         (None, 7, 7, 2048)   1050624     activation_144[0][0]             
__________________________________________________________________________________________________
res5a_branch1 (Conv2D)          (None, 7, 7, 2048)   2099200     activation_142[0][0]             
__________________________________________________________________________________________________
bn5a_branch2c (BatchNormalizati (None, 7, 7, 2048)   8192        res5a_branch2c[0][0]             
__________________________________________________________________________________________________
bn5a_branch1 (BatchNormalizatio (None, 7, 7, 2048)   8192        res5a_branch1[0][0]              
__________________________________________________________________________________________________
add_45 (Add)                    (None, 7, 7, 2048)   0           bn5a_branch2c[0][0]              
                                                                 bn5a_branch1[0][0]               
__________________________________________________________________________________________________
activation_145 (Activation)     (None, 7, 7, 2048)   0           add_45[0][0]                     
__________________________________________________________________________________________________
res5b_branch2a (Conv2D)         (None, 7, 7, 512)    1049088     activation_145[0][0]             
__________________________________________________________________________________________________
bn5b_branch2a (BatchNormalizati (None, 7, 7, 512)    2048        res5b_branch2a[0][0]             
__________________________________________________________________________________________________
activation_146 (Activation)     (None, 7, 7, 512)    0           bn5b_branch2a[0][0]              
__________________________________________________________________________________________________
res5b_branch2b (Conv2D)         (None, 7, 7, 512)    2359808     activation_146[0][0]             
__________________________________________________________________________________________________
bn5b_branch2b (BatchNormalizati (None, 7, 7, 512)    2048        res5b_branch2b[0][0]             
__________________________________________________________________________________________________
activation_147 (Activation)     (None, 7, 7, 512)    0           bn5b_branch2b[0][0]              
__________________________________________________________________________________________________
res5b_branch2c (Conv2D)         (None, 7, 7, 2048)   1050624     activation_147[0][0]             
__________________________________________________________________________________________________
bn5b_branch2c (BatchNormalizati (None, 7, 7, 2048)   8192        res5b_branch2c[0][0]             
__________________________________________________________________________________________________
add_46 (Add)                    (None, 7, 7, 2048)   0           bn5b_branch2c[0][0]              
                                                                 activation_145[0][0]             
__________________________________________________________________________________________________
activation_148 (Activation)     (None, 7, 7, 2048)   0           add_46[0][0]                     
__________________________________________________________________________________________________
res5c_branch2a (Conv2D)         (None, 7, 7, 512)    1049088     activation_148[0][0]             
__________________________________________________________________________________________________
bn5c_branch2a (BatchNormalizati (None, 7, 7, 512)    2048        res5c_branch2a[0][0]             
__________________________________________________________________________________________________
activation_149 (Activation)     (None, 7, 7, 512)    0           bn5c_branch2a[0][0]              
__________________________________________________________________________________________________
res5c_branch2b (Conv2D)         (None, 7, 7, 512)    2359808     activation_149[0][0]             
__________________________________________________________________________________________________
bn5c_branch2b (BatchNormalizati (None, 7, 7, 512)    2048        res5c_branch2b[0][0]             
__________________________________________________________________________________________________
activation_150 (Activation)     (None, 7, 7, 512)    0           bn5c_branch2b[0][0]              
__________________________________________________________________________________________________
res5c_branch2c (Conv2D)         (None, 7, 7, 2048)   1050624     activation_150[0][0]             
__________________________________________________________________________________________________
bn5c_branch2c (BatchNormalizati (None, 7, 7, 2048)   8192        res5c_branch2c[0][0]             
__________________________________________________________________________________________________
add_47 (Add)                    (None, 7, 7, 2048)   0           bn5c_branch2c[0][0]              
                                                                 activation_148[0][0]             
__________________________________________________________________________________________________
activation_151 (Activation)     (None, 7, 7, 2048)   0           add_47[0][0]                     
__________________________________________________________________________________________________
avg_pool (AveragePooling2D)     (None, 1, 1, 2048)   0           activation_151[0][0]             
__________________________________________________________________________________________________
flatten_2 (Flatten)             (None, 2048)         0           avg_pool[0][0]                   
__________________________________________________________________________________________________
fc1000 (Dense)                  (None, 1000)         2049000     flatten_2[0][0]                  
==================================================================================================
Total params: 25,636,712
Trainable params: 25,583,592
Non-trainable params: 53,120
__________________________________________________________________________________________________

#我们可以用下边的代码可视化一下
tf.keras.utils.plot_model(
    model,
    to_file='model inceptionv3.png',
    show_shapes=False,
    show_layer_names=True,
    rankdir='TB',
    expand_nested=False,
    dpi=96
)

在这里插入图片描述

一只很菜很菜的tfer
关注
  • 1
    点赞
  • 踩
  • 4
    收藏
    觉得还不错? 一键收藏
  • 1
    评论
专栏目录
resnet-18 网络 训练cifar100数据-tf2.0-详细注释
weixin_44140703的博客
12-09 2512
resnet.py import tensorflow as tf from tensorflow import keras from tensorflow.keras import layers, Sequential class BasicBlock(layers.Layer): # 继承自layers.layer 这个父类。实现2个基本函数：__init__ 初始化函数...
TensorFlow2.0 搭建简单的ResNet和训练
mathlxj的博客
02-22 2411
1.resnet.py import os import tensorflow as tf from tensorflow import keras from tensorflow.keras import datasets, layers, optimizers, Sequential, metrics class BasicBlock(layers.Layer): def __ini...
Faster RCNN(目标检测算法)（1）
weixin_43227526的博客
07-03 702
Faster RCNN目标检测算法（Two-stage目标检测算法） https://blog.csdn.net/daodanxiansheng/article/details/83340773 Two - stage 和One - stage目标检测算法的综述。 Two-stage目标检测算法
tensorflow实现resnet50（训练+测试+模型转换）
gm_Ergou的博客
07-05 5590
本章使用tensorflow训练resnet50，使用手写数字图片作为数据集。 数据集： 代码工程： 1.train.py import argparse import cv2 import tensorflow as tf # from create_model import resnet_v2_50 from create_model import resnet_v2_50 import numpy as np from data_loader import get_data, g
日月光华tensorflow2.0实战教程全部课件
12-19
在“日月光华tensorflow2.0实战教程”中，你将深入学习 TensorFlow 2.0 的核心概念和实践技巧。以下是该教程可能涵盖的一些关键知识点： 1. **Eager Execution**： - Eager Execution 是 TensorFlow 2.0 的一个...
tensorflow2.0_course
05-13
《TensorFlow 2.0 全面解析：从入门到精通》 ...本课程的"tensorflow2.0_course"包含完整的代码示例，覆盖以上各个知识点，通过实践操作，你将能深入理解和掌握TensorFlow 2.0的所有关键特性和应用。
精品--遥感图像的语义分割，基于深度学习，在Tensorflow框架下，利用TF.Keras，运行环境TF2.0+.zip
最新发布
02-05
通过阅读和理解这些文件，你可以更深入地了解如何在TensorFlow 2.0+和TF.Keras中实现遥感图像的语义分割。 总之，这个项目提供了一个实践深度学习应用于遥感图像语义分割的机会，涵盖了数据预处理、模型构建、训练...
Tensorflow2.0之图像说明文字生成
12-21
在TensorFlow 2.0中，我们可以利用序列到序列（Seq2Seq）模型，结合注意力机制来实现这一目标。 **1. 项目介绍** 此项目的目标是训练一个模型，当给定一张图像时，能输出一段描述图像内容的文字。通常，这个任务...
tf2_yolo_v2.zip
05-28
在TF2.0中实现YOLOv2，开发者可以利用其丰富的库和工具，如Keras API来构建模型，优化器如Adam，以及数据加载器来处理预处理和批处理。 在文件列表中，"readme.txt"可能是提供关于如何安装依赖、运行代码和理解结果...
resnet18-tf2:ResNet-18的简单TensorFlow 2实现
04-02
resnet18-tf2 TensorFlow ResNet的正式似乎未包括ResNet-18或ResNet-34。 该代码库提供了ResNet-18和ResNet-34的简单（ ）TensorFlow 2实现，直接从PyTorch的torchvision转换而来。 模型输出已经过验证，可与火炬视觉模型的输出以浮点精度匹配。 此代码已使用以下软件包版本进行了测试： tensorflow==2.4.1 pytorch==1.2.0 torchvision==0.4.0
pytorch学习视频百度网盘链接.txt
02-23
pytorch学习视频，2.5个G。包括 深度学习初见/ 开发环境安装/ 回归问题/ pytorch基础教程/ pytorch进阶教程/ 随机梯度下降/ 神经网络与全连接层/ 过拟合/ 卷积神经网络CNN/ CIFAR10与resnet实战/ 循环神经网络RNN&lstm/
TensorFlow2.0_ResNet:使用TensorFlow-2.0的ResNet（ResNet18，ResNet34，ResNet50，ResNet101，ResNet152）实现
05-22
TensorFlow2.0_ResNet 使用TensorFlow-2.0的ResNet（ ResNet18，ResNet34，ResNet50，ResNet101，ResNet152 ）实现 有关更多的CNN，请参见 。 火车 要求： Python> = 3.6 Tensorflow == 2.0.0 要在自己的数据集上训练ResNet，可以将数据集放在原始数据集文件夹下，目录应如下所示： |——original dataset |——class_name_0 |——class_name_1 |——class_name_2 |——class_name_3 运行脚本split_dataset.py将原始数据集拆分为训练集，有效集和测试集。 更改config.py中的相应参数。 运行train.py开始培训。 评估 运行valuate.py评估模型在测
利用tensorflow实现经典神经网络（一）-resnet
sinat_37554070的博客
05-17 8531
本文将从三个方面来讲解resnet的实现，分别是resnet的由来，resnet的原理以及resnet的tensorflow实现。1 resnet的提出ResNet最初的灵感出自这个问题：深度学习网络的深度对最后的分类和识别的效果有着很大的影响，所以正常想法就是能把网络设计的越深越好，但是事实上却不是这样，常规的网络的堆叠（plain network）在网络很深的时候，效果却越来越差了，即准确率会...
tensorflow2.0复现resnetv1，v2
weixin_43886213的博客
07-22 1709
1.导入的包 import tensorflow as tf from tensorflow import keras from tensorflow.keras.layers import Conv2D, BatchNormalization, Activation, Dense 2.resnetv1和resnetv2的区别 我认为v1，和v2的基本区别在于v1是Conv->BN-&gt...
使用TensorFlow实现ResNet
CVAIDL的博客
03-28 673
作为在ILSVRC 2015比赛中取得了冠军的网络结构，ResNet借鉴吸收了以往的网络结构的优点，完全抛弃了全连接层，使用残差学习方法解决了在信息传递时出现的信息丢失，损耗等问题，使整个网络只需要学习输入，输出差别的那一部分，简化了学习目标和学习难度。 忽略掉繁琐的解释和代码逻辑实现，我们现在简单地讲解一下RetNet的实现原理，并且利用这些原理便可以看懂相关的代码甚至写出自己的Re...
TF2.0深度学习实战（七）：手撕深度残差网络ResNet
热门推荐
不积跬步，无以至千里！
04-19 1万+
手把手带你搭建网络模型，实现图像分类与目标检测。大神勿扰~
【TF2.0】From_Residual_Networks_v2a
menghaocheng的专栏
12-15 568
将Coursera上吴恩达的教程《Convolutional Neural Networks》第2周的练习2代码转成TF2.0 import tensorflow as tf from matplotlib.pyplot import imshow from tensorflow.keras.utils import plot_model from kt_utils import...
tf2.0使用官方resnet50 finetune
qq_37668436的博客
10-20 611
前言 没咋用tf了，入门学的tf，一堆sess整的最后不想看了…解除了pytorch还是torch好用，最近“机缘巧合”接了个tf的活，记录一下。 finetune官方模型 核心比较简单： r50_finetune = tf.keras.models.Sequential() model = tf.keras.applications.resnet50.ResNet50(input_shape = (img_size,img_size,3), weights="imagenet", include_top
tensorflow2.0实现resnet50
06-28
import tensorflow as tf from tensorflow.keras.applications.resnet50 import ResNet50 from tensorflow.keras.layers import Dense, Flatten from tensorflow.keras.models import Model # 加载ResNet50模型 ...
评论 1
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