我'm training a convolutional autoencoder for IR faces, this is my first time doing autoencoder. I have about 1300 training images, and I didn'吨使用任何调节方法 . 这是我在800个时代之后得到的：top: test images, bottom: output from autoencoder .
这是我的训练曲线：top: training loss, bottom: validation loss . 验证丢失使用与训练集分离的测试集图像 . 最后，训练损失约为0.006，但验证损失为0.009 .
我的模型定义如下，输入图像大小为110X150，输出图像大小为88X120 . 我只是调整源图像的大小来制作训练标签 . 通过除以255对每个样本/标签进行归一化 . 至于该网络的体系结构，我使用这种类似的RGB图像面部特征的布局读取了一篇论文，并且为了我的目的，我将每个层的深度（通道）减半 .
所以我的问题是，有什么不对吗？训练曲线对我来说很奇怪 . 我该如何改进这个自动编码器？更多时代？条例？选择另一个激活功能（我听说泄漏ReLU更好） . 任何反馈和建议表示赞赏，谢谢！
def create_models():
input_img = Input(shape=(150, 110, 1)) # adapt this if using `channels_first` image data format
x = Conv2D(128, (3, 3), activation='relu', padding='same')(input_img)
x = MaxPooling2D((2, 2), padding='same')(x)
x = Conv2D(128, (3, 3), activation='relu', padding='same')(x)
x = MaxPooling2D((2, 2), padding='same')(x)
x = Conv2D(256, (3, 3), activation='relu')(x)
x = MaxPooling2D((2, 2), padding='same')(x)
x = Conv2D(512, (3, 3), activation='relu')(x)
encoded = MaxPooling2D((2, 2), padding='same')(x)
# at this point the representation is (8, 6, 512) i.e. 128-dimensional
x = Conv2D(512, (3, 3), activation='relu', padding='same')(encoded)
x = UpSampling2D((2, 2))(x)
x = Conv2D(256, (3, 3), activation='relu', padding='same')(x)
x = UpSampling2D((2, 2))(x)
x = Conv2D(128, (3, 3), activation='relu')(x)
x = UpSampling2D((2, 2))(x)
x = Conv2D(128, (3, 3), activation='relu', padding='same')(x)
x = UpSampling2D((2, 2))(x)
decoded = Conv2D(1, (3, 3), activation='tanh', padding='same')(x)
autoencoder = Model(input_img, decoded)
autoencoder.compile(optimizer='adadelta', loss='mean_squared_error')
return autoencoder