十的NA代价函数

Question

这是我的密码：

import pandas as pd
import tensorflow as tf
import numpy

#download csv data sheet of all cell lines
input_data = pd.read_csv(
    'C:xxxxxxxxxxxxxxxxxx/xxx/xxx.csv',
    index_col=[0, 1],
    header=0,
    na_values='---')
matrix_data = input_data.as_matrix()

#user define cell lines of interest for supervised training
group1 = input("Please enter cell lines that makes up the your cluster of interest with spaces in between(case sensitive):")
group_split1 = group1.split(sep=" ")

#assign label of each: input cluster = 1
#                      rest of cluster = 0
#extract data of input group
g1 = input_data.loc[:,group_split1]
g2 = input_data.loc[:,[x for x in list(input_data) if x not in group_split1]]
regroup = pd.concat([g1,g2], axis=1, join_axes=[g1.index])
regroup = numpy.transpose(regroup.as_matrix())

labels = numpy.zeros(shape=[len(regroup),1])
labels[0:len(group_split1)] = 1

#define variables
trainingtimes = 1000

#create model
x = tf.placeholder(tf.float32, [None, 54781])
w = tf.Variable(tf.zeros([54781,1]))
b = tf.Variable(tf.zeros([1]))
#define linear regression model, loss function
y = tf.nn.sigmoid((tf.matmul(x,w)+b))

#define correct training group
ytt = tf.placeholder(tf.float32, [None, 1])

#define cross optimizer and cost function
mse = tf.reduce_mean(tf.losses.mean_squared_error(y, ytt))

#train step
train_step = tf.train.GradientDescentOptimizer(learning_rate=0.1).minimize(mse)

sess = tf.InteractiveSession()
tf.global_variables_initializer().run()

for i in range(trainingtimes):
    sess.run(train_step, feed_dict={x: regroup, ytt:labels})
    if i%100 == 0:
        print(sess.run(mse, feed_dict={x:regroup, ytt:labels}))

我输入的x和y数据：x是一个141*54871的矩阵，每行代表一个细胞，每54871列代表该细胞（该行）基因的基因表达水平。y是一个141*1的单列标签，通过将组1或2的单元格标记为0或1来区分组1和组2。你知道吗

我的成本函数mse只打印nan。神经元过多有什么问题吗？或者是什么问题？谢谢您！你知道吗

Answer 1

占位符x被for循环中的整数x覆盖。所以feed_dict中的变量x是来自range(trainingtimes)的变量，它绝对不是TF张量。你知道吗

重命名变量x以避免问题：

for i in range(trainingtimes):
    sess.run(train_step, feed_dict={x: regroup, ytt:labels})
    if i % 100 == 0:
        print(sess.run(mse, feed_dict={x:regroup, ytt:labels}))