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
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: 6,763,777Trainable params: 6,751,233Non-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: 3,485,441Trainable params: 3,485,441Non-trainable params: 0_________________________________________________________________-11-24 21:53:56.659897: I tensorflow/core/platform/: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 1024model.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 modeldef 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 modelg = generator_model()g.summary()d = discriminator_model()d.summary()
