如何合并两个不同的模型并在 tensorflow 中训练？

Question

我一直在寻找使用 Tensorflow 实现深度学习模型的信息，最后我在这里问，因为我无法挖掘出来。这可能是一个非常基本的问题，但我会感谢您的友好回复。

import tensorflow as tf
import random
import os
import numpy as np
import time
import random
import csv
from random import shuffle

np.random.seed(1117)    
# for reproduct

# parameters
learning_rate = 1E-5 * 5

batch_size_SE = 2500
batch_size_STOI = 50

spl = 5
frames = 50
con_frame = 50

feature_dim = 256

nb_epoch = 50
layer_width = 2048

training_length = 500
validation_length = 50

keep_prob = tf.placeholder(tf.float32)

# SE_input/output placeholders
X = tf.placeholder(tf.float32, [batch_size_SE, feature_dim*(2*spl+1)])
Y = tf.placeholder(tf.float32, [batch_size_SE, feature_dim])

# STOI_input/output placeholders
STOI_feature = tf.placeholder(tf.float32, [batch_size_STOI, feature_dim*frames*2])
STOI_target = tf.placeholder(tf.float32, [batch_size_STOI, 1])



#########################Speech enhancement DNN#########################

# SE_1st Hidden layer
W11 = tf.get_variable("W11", shape=[(2*spl+1)*feature_dim,layer_width], initializer=tf.contrib.layers.xavier_initializer())
b11 = tf.Variable(tf.random_normal([layer_width]))
L11 = tf.nn.relu(tf.matmul(X, W11) + b11)
L11 = tf.nn.dropout(L11, keep_prob=keep_prob)

# SE_2nd Hidden layer   
W12 = tf.get_variable("W12", shape=[layer_width,layer_width], initializer=tf.contrib.layers.xavier_initializer())
b12 = tf.Variable(tf.random_normal([layer_width]))
L12 = tf.nn.relu(tf.matmul(L11, W12)+ b12)
L12 = tf.nn.dropout(L12, keep_prob=keep_prob)

# SE_3rd Hidden layer
W13 = tf.get_variable("W23", shape=[layer_width, layer_width], initializer=tf.contrib.layers.xavier_initializer())
b13 = tf.Variable(tf.random_normal([layer_width]))
L13 = tf.nn.relu(tf.matmul(L12, W13) + b13)
L13 = tf.nn.dropout(L13, keep_prob=keep_prob)

# SE_4th Hidden layer
W14 = tf.get_variable("W14", shape=[layer_width,layer_width], initializer=tf.contrib.layers.xavier_initializer())   
b14 = tf.Variable(tf.random_normal([layer_width]))
L14 = tf.nn.relu(tf.matmul(L13, W14)+ b14)
L14 = tf.nn.dropout(L14, keep_prob=keep_prob)

# enhanced_speech_output layer
W15 = tf.get_variable("W15", shape=[layer_width,feature_dim], initializer=tf.contrib.layers.xavier_initializer())   
b15 = tf.Variable(tf.random_normal([feature_dim]))
SE_hypothesis = tf.matmul(L14, W15) + b15



#########################STOI estimation DNN#########################

# STOI_1st Hidden layer
W21 = tf.get_variable("W21", shape=[feature_dim*frames*2,layer_width], initializer=tf.contrib.layers.xavier_initializer())
b21 = tf.Variable(tf.random_normal([layer_width]))
L21 = tf.nn.relu(tf.matmul(X, W21) + b21)
L21 = tf.nn.dropout(L21, keep_prob=keep_prob)

# STOI_2nd Hidden layer 
W22 = tf.get_variable("W22", shape=[layer_width,layer_width], initializer=tf.contrib.layers.xavier_initializer())
b22 = tf.Variable(tf.random_normal([layer_width]))
L22 = tf.nn.relu(tf.matmul(L1, W22)+ b22)
L22 = tf.nn.dropout(L22, keep_prob=keep_prob)

# STOI_3rd Hidden layer
W23 = tf.get_variable("W23", shape=[layer_width, layer_width], initializer=tf.contrib.layers.xavier_initializer())
b23 = tf.Variable(tf.random_normal([layer_width]))
L23 = tf.nn.relu(tf.matmul(L22, W23) + b23)
L23 = tf.nn.dropout(L23, keep_prob=keep_prob)

# STOI_4th Hidden layer
W24 = tf.get_variable("W24", shape=[layer_width,layer_width], initializer=tf.contrib.layers.xavier_initializer())   
b24 = tf.Variable(tf.random_normal([layer_width]))
L24 = tf.nn.relu(tf.matmul(L23, W24)+ b24)
L24 = tf.nn.dropout(L24, keep_prob=keep_prob)

# enhanced_speech_output layer
W25 = tf.get_variable("W25", shape=[layer_width,1], initializer=tf.contrib.layers.xavier_initializer()) 
b25 = tf.Variable(tf.random_normal([1]))
STOI_hypothesis = tf.matmul(L24, W25) + b25



#########################Cost function and optimizer#########################

SE_var_list = [W11, W12, W13, W14, W15, b11, b12, b13, b14, b15]

cost = tf.reduce_mean(tf.square(STOI_target - STOI_hypothesis))

optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost, var_list = SE_var_list)

saver = tf.train.Saver()

现在，我想使用一种方法来训练两个神经工作模型。 DNN1，这是我要训练的模型，DNN2 是已经训练好的模型。我尝试用tensorflow构建这两个模型的框架。但是，它有一条错误消息“尺寸必须相等，但为 2816 和 25600”。我觉得我不应该像传统的 tensorflow DNN 那样训练，所以请问我可以用什么样的方法来修改代码。

Answer 1

你问了一个非常广泛的问题。弹出的错误意味着您正在尝试将值提供给具有不同维度的张量。

我将坚持使用您在图片中发布的 DNN，尽管您开始后似乎很难，但看起来更容易，我不会给您代码，但我会给您说明您应该做什么：

import tensorflow as tf
INT = tf.int32

def graph_add():
    g = tf.Graph()
    with g.as_default() as g:
        a = tf.placeholder(INT, [], name='a')
        b = tf.placeholder(INT, [], name='b')
        c = tf.add(a, b, name='c')
    return g.as_graph_def()

def graph_pow():
     g = tf.Graph()
    with g.as_default() as g:
        d = tf.placeholder(INT, [], name='d')
        e = tf.pow(d, 2, name='e')
    return g.as_graph_def()

tf.reset_default_graph()

# input of the main graph
a = tf.placeholder(INT, [], name='a')
b = tf.placeholder(INT, [], name='b')

# connect a, b to graph_add, output is g1_c
[g1_c] = tf.import_graph_def(
    graph_add(), input_map={'a': a,
                            'b': b}, return_elements=['c:0'])

# connect output of graph add, g1_c, as input of graph_pow, output is g2_e
[g2_e] = tf.import_graph_def(
    graph_pow(), input_map={'d': g1_c}, return_elements=['e:0'])

# get results of g1_c and g2_e
with tf.Session() as sess:
    c, e = sess.run([g1_c, g2_e], feed_dict={a: 10, b: 20})
    print('a + b =', c)
    print('(a + b)^2 =', e)

此代码来自here，它是合并两个不同图形的关键。您需要做的是为您的目的在第二个图中加载您训练的模型，它应该可以工作。我挑战你尝试自己做，你会学到很多东西。如果你是 TF 的初学者，我建议你先尝试一些更简单的东西，也许是 MNIST？

希望对你有所帮助！

PD：我只是好奇，你能告诉我你在训练什么吗？