尺寸必须相等，但对于输入形状为[1,15]，[1,500]的'MatMul_1'（op：'MatMul'），尺寸应为15和1

Question

我无法理解尺寸部分。 与我设定的[1,15]形状有关吗？

import tensorflow as tf
import numpy as np
import pandas as pd



with open('train.CSV', 'r') as f:  
    data0 = f.readlines()  

    for line in data0:  
        odom = line.split()         
        numbers_float0 = map(float, odom) 

with open('trainY.CSV', 'r') as f:  
    data1 = f.readlines()  

for line in data1:  
    odom = line.split()        
    numbers_float1 = map(float, odom)  

with open('test.CSV', 'r') as f:  
    data2 = f.readlines()  

    for line in data2:  
        odom = line.split()        
        numbers_float2 = map(float, odom) 

with open('Test Y.CSV', 'r') as f:  
    data3 = f.readlines()    

    for line in data3:  
        odom = line.split()      
        numbers_float3 = map(float, odom)  



train_x,train_y,test_x,test_y =             ('numbers_float0','numbers_float1','numbers_float2','numbers_float3')
n_nodes_hl1 = 500
n_nodes_hl2 = 500
n_nodes_hl3 = 500

n_classes = 2
batch_size = 100
hm_epochs = 10

x =tf.placeholder('float',[1,15])  
y = tf.placeholder('float',[1,1])

hidden_1_layer = {'f_fum':n_nodes_hl1,
                  'weight':tf.Variable(tf.random_normal([len(train_x[0]),         n_nodes_hl1])),
                  'bias':tf.Variable(tf.random_normal([n_nodes_hl1]))}

hidden_2_layer = {'f_fum':n_nodes_hl2,
                  'weight':tf.Variable(tf.random_normal([n_nodes_hl1, n_nodes_hl2])),
                  'bias':tf.Variable(tf.random_normal([n_nodes_hl2]))}

hidden_3_layer = {'f_fum':n_nodes_hl3,
                  'weight':tf.Variable(tf.random_normal([n_nodes_hl2, n_nodes_hl3])),
              'bias':tf.Variable(tf.random_normal([n_nodes_hl3]))}

output_layer = {'f_fum':None,
            'weight':tf.Variable(tf.random_normal([n_nodes_hl3, n_classes])),
                'bias':tf.Variable(tf.random_normal([n_classes])),}


# Nothing changes
def neural_network_model(data):

    l1 = tf.add(tf.matmul(data,hidden_1_layer['weight']),     hidden_1_layer['bias'])
    l1 = tf.nn.relu(l1)

    l2 = tf.add(tf.matmul(l1,hidden_2_layer['weight']),     hidden_2_layer['bias'])
    l2 = tf.nn.relu(l2)

    l3 = tf.add(tf.matmul(l2,hidden_3_layer['weight']), hidden_3_layer['bias'])
    l3 = tf.nn.relu(l3)

    output = tf.matmul(l3,output_layer['weight']) + output_layer['bias']

    return output

def train_neural_network(x):
    prediction = neural_network_model(x)
    cost =     tf.reduce_sum(tf.nn.softmax_cross_entropy_with_logits(logits=prediction, labels=y))
    #tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits(prediction,y) )




    optimizer = tf.train.AdamOptimizer(learning_rate=0.001).minimize(cost)

    with tf.Session() as sess:
        sess.run(tf.initialize_all_variables())

        for epoch in range(hm_epochs):
            epoch_loss = 0
            i=0
            while i < len(train_x):
                start = i
                end = i+batch_size
                batch_x = np.array(train_x[start:end])
                batch_y = np.array(train_y[start:end])

                _, c = sess.run([optimizer, cost], feed_dict={x: batch_x,
                                                          y: batch_y})
                epoch_loss += c
                i+=batch_size

            print('Epoch', epoch+1, 'completed out of',hm_epochs,'loss:',epoch_loss)
        correct = tf.equal(tf.argmax(prediction, 1), tf.argmax(y, 1))
        accuracy = tf.reduce_mean(tf.cast(correct, 'float'))

        print('Accuracy:',accuracy.eval({x:test_x, y:test_y}))


train_neural_network(x)

这是跟踪错误： 在此处输入图像描述

这是数据火车。CSV 在此处输入图像描述

我使用的Y数据只有一列。

Answer 1

从技术上讲，占位符根本不需要形状。 可以这样定义。

x = tf.placeholder('float', shape=[])

在这种情况下，占位符本身没有形状信息。 如果您知道张量的尺寸，但不知道其实际的数字形状，则可以将该尺寸的数值替换为None，因为它可以具有可变的尺寸。

 x = tf.placeholder('float', shape=[None, None, None])

这会影响一些下游静态形状分析，而张量流确实会进行这种静态形状分析以获取形状信息，但否则它仍应按预期工作。