Keras自动编码器：从编码器到解码器的捆绑重量不起作用

Question

我正在创建一个自动编码器作为我的完整模型的一部分，为一个卡格尔比赛。我试着把编码器的重量，转置到解码器上。在第一个历元之前，权值是正确同步的，之后，解码器的权重就冻结了，跟不上由梯度下降而更新的编码器权重。在

我在google上找到的几乎每一篇关于这个问题的帖子都花了12个小时，似乎没有人能回答我的问题。最接近的一个是这个Tying Autoencoder Weights in a Dense Keras Layer，但是这个问题是通过不使用变量张量作为内核来解决的，但是我已经没有使用这种张量作为我的解码器内核，所以没有用。在

Im使用的是本文中定义的denseted Keras自定义层类，https://towardsdatascience.com/build-the-right-autoencoder-tune-and-optimize-using-pca-principles-part-ii-24b9cca69bd6，完全相同，只是改变了引用Keras支持的方式，以适合我的导入风格。在

import tensorflow as tf
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import os

这是自定义图层定义

^{pr2}$

这是一个虚拟数据集的模型训练和测试

rand_samples = np.random.rand(16, 51)
dummy_ds = tf.data.Dataset.from_tensor_slices((rand_samples, rand_samples)).shuffle(16).batch(16)

encoder = tf.keras.layers.Dense(1, activation="linear", input_shape=(51,), use_bias=True)
decoder = DenseTied(51, activation="linear", tied_to=encoder, use_bias=True)

autoencoder = tf.keras.Sequential()
autoencoder.add(encoder)
autoencoder.add(decoder)

autoencoder.compile(metrics=['accuracy'],
                    loss='mean_squared_error',
                    optimizer='sgd')

autoencoder.summary()

print("Encoder Kernel Before 1 Epoch", encoder.kernel[0])
print("Decoder Kernel Before 1 Epoch", decoder.kernel[0][0])

autoencoder.fit(dummy_ds, epochs=1)

print("Encoder Kernel After 1 Epoch", encoder.kernel[0])
print("Decoder Kernel After 1 Epoch", decoder.kernel[0][0])

预期的输出是第一个元素中的两个内核完全相同（为了简单起见，只打印一个权重）

当前输出显示解码器内核的更新与转置编码器内核的更新不同

2019-09-06 14:55:42.070003: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library nvcuda.dll
2019-09-06 14:55:42.984580: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1640] Found device 0 with properties:
name: GeForce GTX 1060 major: 6 minor: 1 memoryClockRate(GHz): 1.733
pciBusID: 0000:01:00.0
2019-09-06 14:55:43.088109: I tensorflow/stream_executor/platform/default/dlopen_checker_stub.cc:25] GPU libraries are statically linked, skip dlopen check.        
2019-09-06 14:55:43.166145: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1763] Adding visible gpu devices: 0
2019-09-06 14:55:43.203865: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2
2019-09-06 14:55:43.277988: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1640] Found device 0 with properties:
name: GeForce GTX 1060 major: 6 minor: 1 memoryClockRate(GHz): 1.733
pciBusID: 0000:01:00.0
2019-09-06 14:55:43.300888: I tensorflow/stream_executor/platform/default/dlopen_checker_stub.cc:25] GPU libraries are statically linked, skip dlopen check.        
2019-09-06 14:55:43.309040: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1763] Adding visible gpu devices: 0
2019-09-06 14:55:44.077814: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1181] Device interconnect StreamExecutor with strength 1 edge matrix:
2019-09-06 14:55:44.094542: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1187]      0
2019-09-06 14:55:44.099411: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1200] 0:   N
2019-09-06 14:55:44.103424: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1326] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4712 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1060, pci bus id: 0000:01:00.0, compute capability: 6.1)
Model: "sequential"
_________________________________________________________________
Layer (type)                 Output Shape              Param #
=================================================================
dense (Dense)                (None, 1)                 52
_________________________________________________________________
dense_tied (DenseTied)       (None, 51)                103
=================================================================
Total params: 103
Trainable params: 103
Non-trainable params: 0
_________________________________________________________________
Encoder Kernel Before 1 Epoch tf.Tensor([0.20486075], shape=(1,), dtype=float32)
Decoder Kernel Before 1 Epoch tf.Tensor(0.20486075, shape=(), dtype=float32)
1/1 [==============================] - 1s 657ms/step - loss: 0.3396 - accuracy: 0.0000e+00
Encoder Kernel After 1 Epoch tf.Tensor([0.20530733], shape=(1,), dtype=float32)
Decoder Kernel After 1 Epoch tf.Tensor(0.20486075, shape=(), dtype=float32)
PS C:\Users\whitm\Desktop\CodeProjects\ForestClassifier-DEC>

我看不出我做错了什么。在

Answer 1

为了平衡权重，我建议使用Keras functional API来共享层。也就是说，这里有一个替代实现，它将编码器和解码器之间的权重联系起来：

class TransposableDense(tf.keras.layers.Dense):

    def __init__(self, units, **kwargs):
        super().__init__(units, **kwargs)

    def build(self, input_shape):
        assert len(input_shape) >= 2
        input_dim = input_shape[-1]
        self.t_output_dim = input_dim

        self.kernel = self.add_weight(shape=(int(input_dim), self.units),
                                      initializer=self.kernel_initializer,
                                      name='kernel',
                                      regularizer=self.kernel_regularizer,
                                      constraint=self.kernel_constraint)
        if self.use_bias:
            self.bias = self.add_weight(shape=(self.units,),
                                        initializer=self.bias_initializer,
                                        name='bias',
                                        regularizer=self.bias_regularizer,
                                        constraint=self.bias_constraint)
            self.bias_t = self.add_weight(shape=(input_dim,),
                                          initializer=self.bias_initializer,
                                          name='bias_t',
                                          regularizer=self.bias_regularizer,
                                          constraint=self.bias_constraint)
        else:
            self.bias = None
            self.bias_t = None
        # self.input_spec = tf.keras.layers.InputSpec(min_ndim=2, axes={-1: input_dim})
        self.built = True

    def call(self, inputs, transpose=False):
        bs, input_dim = inputs.get_shape()

        kernel = self.kernel
        bias = self.bias
        if transpose:
            assert input_dim == self.units
            kernel = tf.keras.backend.transpose(kernel)
            bias = self.bias_t

        output = tf.keras.backend.dot(inputs, kernel)
        if self.use_bias:
            output = tf.keras.backend.bias_add(output, bias, data_format='channels_last')
        if self.activation is not None:
            output = self.activation(output)
        return output

    def compute_output_shape(self, input_shape):
        bs, input_dim = input_shape
        output_dim = self.units
        if input_dim == self.units:
            output_dim = self.t_output_dim
        return bs, output_dim

这个密集层的内核可以通过调用transpose=True的层来进行转换。请注意，这可能会打破Keras的一些基本原则（例如，层有多个输出形状），但它应该适用于您的情况。在

---

下面是一个示例，演示如何使用它定义模型：

^{pr2}$

Answer 2

重量没有系好。您只是用第一层的转置权重初始化绑定层的权重，然后再也不要训练它们。^{cd1>}返回一个新的张量/不同的对象，并^{cd2>}创建一个新变量，因此在^{{cd3>}之后，两层之间的任何关系都会丢失。我想最好这样做：

def call(self, inputs):
    output = tf.keras.backend.dot(inputs, tf.keras.backend.transpose(self.tied_to.kernel))
    if self.use_bias:
        output = tf.keras.backend.bias_add(output, self.tied_to.bias, data_format='channels_last')
    if self.activation is not None:
        output = self.activation(output)
    return output

在这里，绑定层始终显式地使用第一层的权重，并且不会有任何权重本身（即从^{{cd3>}中删除^{cd2>}部分）。