Skip to main content
 首页 » 编程设计

python之Keras之训练卷积网络,获得自动编码器输出

2025年04月02日17qq78292959

我想做的: 我想在两个类的 cifar10 数据集上训练一个卷积神经网络。然后一旦我得到我的拟合模型,我想获取所有层并重现输入图像。所以我想从网络中取回图像而不是分类。

到目前为止我做了什么:

def copy_freeze_model(model, nlayers = 1): 
    new_model = Sequential() 
    for l in model.layers[:nlayers]: 
      l.trainable = False 
      new_model.add(l) 
    return new_model 
 
numClasses = 2 
(X_train, Y_train, X_test, Y_test) = load_data(numClasses) 
#Part 1 
rms = RMSprop() 
model = Sequential() 
#input shape: channels, rows, columns 
model.add(Convolution2D(32, 3, 3, border_mode='same', 
                        input_shape=(3, 32, 32))) 
model.add(Activation("relu")) 
model.add(MaxPooling2D(pool_size=(2, 2))) 
model.add(Dropout(0.5)) 
 
model.add(Flatten()) 
model.add(Dense(512)) 
model.add(Activation("relu")) 
model.add(Dropout(0.5)) 
#output layer 
model.add(Dense(numClasses)) 
model.add(Activation('softmax')) 
model.compile(loss='categorical_crossentropy', optimizer=rms,metrics=["accuracy"]) 
 
model.fit(X_train,Y_train, batch_size=32, nb_epoch=25, 
          verbose=1, validation_split=0.2, 
          callbacks=[EarlyStopping(monitor='val_loss', patience=2)]) 
print('Classifcation rate %02.3f' % model.evaluate(X_test, Y_test)[1]) 
 
##pull the layers and try to get an output from the network that is image. 
 
newModel = copy_freeze_model(model, nlayers = 8) 
newModel.add(Dense(1024)) 
 
newModel.compile(loss='mean_squared_error', optimizer=rms,metrics=["accuracy"]) 
newModel.fit(X_train,X_train, batch_size=32, nb_epoch=25, 
          verbose=1, validation_split=0.2, 
          callbacks=[EarlyStopping(monitor='val_loss', patience=2)]) 
preds = newModel.predict(X_test) 

还有当我这样做的时候:

input_shape=(3, 32, 32) 

这是否意味着 3 channel (RGB) 32 x 32 图像?

请您参考如下方法:

我建议您使用堆叠式卷积自编码器。这使得去池化层和反卷积成为强制性的。在这里你可以找到 Theano 中的总体思路和代码(Keras 是基于 Theano 构建的):

https://swarbrickjones.wordpress.com/2015/04/29/convolutional-autoencoders-in-pythontheanolasagne/

可以在此处找到所需层的示例定义:

https://github.com/fchollet/keras/issues/378