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
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
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
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)
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()
