DL之DCGAN：基于keras框架利用深度卷积对抗网络DCGAN算法对MNIST数据集实现图像生成

布满荆棘的人生 2022-12-23 11:19 41阅读 0赞

**目录**

基于keras框架利用深度卷积对抗网络DCGAN算法对MNIST数据集实现图像生成

设计思路

输出结果

核心代码

--------------------

**相关文章**  
[DL之DCGAN：基于keras框架利用深度卷积对抗网络DCGAN算法对MNIST数据集实现图像生成][DL_DCGAN_keras_DCGAN_MNIST]  
[DL之DCGAN：基于keras框架利用深度卷积对抗网络DCGAN算法对MNIST数据集实现图像生成实现][DL_DCGAN_keras_DCGAN_MNIST 1]

# 基于keras框架利用深度卷积对抗网络DCGAN算法对MNIST数据集实现图像生成 #

## 设计思路 ##

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzQxMTg1ODY4_size_16_color_FFFFFF_t_70][]

## 输出结果 ##

X像素取值范围是[-1.0, 1.0]
    _________________________________________________________________
    Layer (type)                 Output Shape              Param #   
    =================================================================
    dense_1 (Dense)              (None, 1024)              103424    
    _________________________________________________________________
    activation_1 (Activation)    (None, 1024)              0         
    _________________________________________________________________
    dense_2 (Dense)              (None, 6272)              6428800   
    _________________________________________________________________
    batch_normalization_1 (Batch (None, 6272)              25088     
    _________________________________________________________________
    activation_2 (Activation)    (None, 6272)              0         
    _________________________________________________________________
    reshape_1 (Reshape)          (None, 7, 7, 128)         0         
    _________________________________________________________________
    up_sampling2d_1 (UpSampling2 (None, 14, 14, 128)       0         
    _________________________________________________________________
    conv2d_1 (Conv2D)            (None, 14, 14, 64)        204864    
    _________________________________________________________________
    activation_3 (Activation)    (None, 14, 14, 64)        0         
    _________________________________________________________________
    up_sampling2d_2 (UpSampling2 (None, 28, 28, 64)        0         
    _________________________________________________________________
    conv2d_2 (Conv2D)            (None, 28, 28, 1)         1601      
    _________________________________________________________________
    activation_4 (Activation)    (None, 28, 28, 1)         0         
    =================================================================
    Total params: 6,763,777
    Trainable params: 6,751,233
    Non-trainable params: 12,544
    _________________________________________________________________
    _________________________________________________________________
    Layer (type)                 Output Shape              Param #   
    =================================================================
    conv2d_3 (Conv2D)            (None, 28, 28, 64)        1664      
    _________________________________________________________________
    activation_5 (Activation)    (None, 28, 28, 64)        0         
    _________________________________________________________________
    max_pooling2d_1 (MaxPooling2 (None, 14, 14, 64)        0         
    _________________________________________________________________
    conv2d_4 (Conv2D)            (None, 10, 10, 128)       204928    
    _________________________________________________________________
    activation_6 (Activation)    (None, 10, 10, 128)       0         
    _________________________________________________________________
    max_pooling2d_2 (MaxPooling2 (None, 5, 5, 128)         0         
    _________________________________________________________________
    flatten_1 (Flatten)          (None, 3200)              0         
    _________________________________________________________________
    dense_3 (Dense)              (None, 1024)              3277824   
    _________________________________________________________________
    activation_7 (Activation)    (None, 1024)              0         
    _________________________________________________________________
    dense_4 (Dense)              (None, 1)                 1025      
    _________________________________________________________________
    activation_8 (Activation)    (None, 1)                 0         
    =================================================================
    Total params: 3,485,441
    Trainable params: 3,485,441
    Non-trainable params: 0
    _________________________________________________________________
    2020-11-24 21:53:56.659897: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2
    (25, 28, 28, 1)

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzQxMTg1ODY4_size_16_color_FFFFFF_t_70 1][]![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzQxMTg1ODY4_size_16_color_FFFFFF_t_70 2][]

## 核心代码 ##

def generator_model():
        model = Sequential()
        model.add(Dense(input_dim=100, units=1024))     #  1034  1024
        model.add(Activation('tanh'))
        model.add(Dense(128*7*7))
        model.add(BatchNormalization())
        model.add(Activation('tanh'))
        model.add(Reshape((7, 7, 128), input_shape=(128*7*7,)))
        model.add(UpSampling2D(size=(2, 2)))
        model.add(Conv2D(64, (5, 5), padding='same'))
        model.add(Activation('tanh'))
        model.add(UpSampling2D(size=(2, 2)))
        model.add(Conv2D(1, (5, 5), padding='same'))
        model.add(Activation('tanh'))
        return model
    def discriminator_model():     # 定义鉴别网络：输入一张图像，输出0(伪造)/1(真实)
        model = Sequential()
        model.add(
                Conv2D(64, (5, 5),
                padding='same',
                input_shape=(28, 28, 1))
                )
        model.add(Activation('tanh'))
        model.add(MaxPooling2D(pool_size=(2, 2)))
        model.add(Conv2D(128, (5, 5)))
        model.add(Activation('tanh'))
        model.add(MaxPooling2D(pool_size=(2, 2)))
        model.add(Flatten())
        model.add(Dense(1024))
        model.add(Activation('tanh'))
        model.add(Dense(1))
        model.add(Activation('sigmoid'))
        return model
    
    
    g = generator_model()
    g.summary()
    
    d = discriminator_model()
    d.summary()

[DL_DCGAN_keras_DCGAN_MNIST]: https://yunyaniu.blog.csdn.net/article/details/110097975
[DL_DCGAN_keras_DCGAN_MNIST 1]: https://yunyaniu.blog.csdn.net/article/details/110098166
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzQxMTg1ODY4_size_16_color_FFFFFF_t_70]: /images/20221120/3610ca2d64a146d8ad2f05eaea05ab63.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzQxMTg1ODY4_size_16_color_FFFFFF_t_70 1]: https://img-blog.csdnimg.cn/20201124215342451.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzQxMTg1ODY4,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzQxMTg1ODY4_size_16_color_FFFFFF_t_70 2]: /images/20221120/0e6915476a574e1fb8dd2e04a73b88bf.png