Question

我是tensorflow中的新手，并尝试创建一个模型，该模型将根据INPUT预测X和Y坐标，INPUT由86个变量组成，这些变量决定从位于建筑物中的86个扫描接收的信号强度。我有340个测试数据。我解析它们并将它们放在两个.csv文件中。

第一组包含有序信号强度。我把它保存为data.csv。 data.csv

第二个文件包含当时仪表所在的坐标。我把它保存为labes.csv。 labels.csv

我已经创建了一个模型，但不幸的是它的准确性只改变了两个训练步骤。如果我想制作tf.summary.merge_all（），则会出现此错误：Error message。如果我删除此行，则培训会成功结束，但除前两个步骤外，准确性不会改变： training steps

此处出现错误消息：

Nan的摘要直方图：偏差

 [[Node: Biases = HistogramSummary[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"](Biases/tag, Bias/read)]]

由op＆＃39; Biases＆＃39;引起，定义于：

文件＆＃34; E：\ Programy \ Microsoft Visual Studio 14.0 \ Common7 \ IDE \ Extensions \ Microsoft \ Python工具，用于Visual Studio \ 2.2 \ visualstudio_py_launcher.py＆＃34;，第78行，

vspd.debug(filename, port_num, debug_id, debug_options, run_as)

文件＆＃34; E：\ Programy \ Microsoft Visual Studio 14.0 \ Common7 \ IDE \ Extensions \ Microsoft \ Python工具，用于Visual Studio \ 2.2 \ visualstudio_py_debugger.py＆＃34;，第2483行，在调试中

exec_file(file, globals_obj)

文件＆＃34; E：\ Programy \ Microsoft Visual Studio 14.0 \ Common7 \ IDE \ Extensions \ Microsoft \ Python工具，用于Visual Studio \ 2.2 \ visualstudio_py_util.py＆＃34;，第111行，在exec_file中

exec_code(code, file, global_variables)

文件＆＃34; E：\ Programy \ Microsoft Visual Studio 14.0 \ Common7 \ IDE \ Extensions \ Microsoft \ Python工具，用于Visual Studio \ 2.2 \ visualstudio_py_util.py＆＃34;，第87行，在exec_code中

exec(code_obj, global_variables)

文件＆＃34; C：\ Users \ Tesi \ documents \ visual studio 2015 \ Projects \ LocationDetectionTensorflow \ LocationDetectionTensorflow \ LocationDetectionTensorflow.py＆＃34;，第41行，

tf.summary.histogram("Biases", b)

文件＆＃34; C：\ Users \ Tesi \ AppData \ Local \ Programs \ Python \ Python35 \ lib \ site-packages \ tensorflow \ python \ summary \ summary.py＆＃34;，第193行，直方图< / p>

tag=tag, values=values, name=scope)

文件＆＃34; C：\ Users \ Tesi \ AppData \ Local \ Programs \ Python \ Python35 \ lib \ site-packages \ tensorflow \ python \ ops \ gen_logging_ops.py＆＃34;，第215行，在_histogram_summary < / p>

"HistogramSummary", tag=tag, values=values, name=name)

文件＆＃34; C：\ Users \ Tesi \ AppData \ Local \ Programs \ Python \ Python35 \ lib \ site-packages \ tensorflow \ python \ framework \ op_def_library.py＆＃34;，第787行，在_apply_op_helper < / p>

op_def=op_def)

文件＆＃34; C：\ Users \ Tesi \ AppData \ Local \ Programs \ Python \ Python35 \ lib \ site-packages \ tensorflow \ python \ framework \ ops.py＆＃34;，第3160行，在create_op < / p>

op_def=op_def)

文件＆＃34; C：\ Users \ Tesi \ AppData \ Local \ Programs \ Python \ Python35 \ lib \ site-packages \ tensorflow \ python \ framework \ ops.py＆＃34;，第1625行，初始化

self._traceback = self._graph._extract_stack()  # pylint: disable=protected-access

InvalidArgumentError（参见上面的回溯）：Nan的摘要直方图：偏差

 [[Node: Biases = HistogramSummary[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"](Biases/tag, Bias/read)]]

Data.csv：

100,94,99,100,100,100,100,100,100,100,100,100,100,100,100,90,79,100,100,100,100,100,100,100,100,100,100,100,100,100,100,100,100,100,100,100,100,100,100,100,100,100,100,100,100,100,100,100,100,100,100,100,100,100,100,100,100,100,100,85,100,78,77,79,78,100,100,100,100,100,100,100,100,100,100,100,100,100,100,100,100,100,100,100,100,89

... 100,100,100,100,100,87,100,87,100,97,100,90,90,100,100,100,100,100,100,92,100,100,100,100,95,100,100,100,100,88,100,100,100,100,100,100,100,100,100,100,100,100,100,100,100,100,100,100,100,100,100,100,100,100,100,64,64,74,74,100,100,100,100,100,100,100,73,100,100,100,100,100,100,88,100,100,100,100,100,100,100,100,100,100,100,100

Labels.csv：

450,2300

1750,900 ...

代码在这里：

import tensorflow as tf
import numpy as np

data = np.genfromtxt("dataExcel.csv", delimiter=';')
labels = np.genfromtxt("labelsExcel.csv", delimiter=';')

inputs = 86
outputs = 2

x = tf.placeholder(tf.float32, shape=[None, inputs], name='input_X')
y = tf.placeholder(tf.float32, shape=[None, outputs], name='output_Y')
tf.summary.histogram("input_X",x)
tf.summary.histogram("output_Y",y)

W = tf.Variable(tf.zeros([86, 2]), name="Weight")
b = tf.Variable(tf.zeros([2]), name="Bias")
tf.summary.histogram("Weights", W)
tf.summary.histogram("Biases", b)

with tf.name_scope("softmax") as scope:
    softmax = tf.nn.softmax(tf.matmul(x, W) + b)

with tf.name_scope("cross_entropy_also_cost_function") as scope:
    cross_entropy = -tf.reduce_sum(y*tf.log(softmax))
    tf.summary.scalar("cross_entropy", cross_entropy)

with tf.name_scope("train") as scope:
    optimizer = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)

with tf.name_scope("accuracy"):
    prediction = tf.equal(tf.argmax(softmax,1),tf.argmax(y,1))
    accuracy = tf.reduce_mean(tf.cast(prediction,tf.float32))
    tf.summary.scalar("accuracy", accuracy)

merged_summary = tf.summary.merge_all()
init = tf.global_variables_initializer()
with tf.Session() as sess:
    sess.run(init)
    avg_cost = 0.
    writer = tf.summary.FileWriter("/tmp/Location")
    writer.add_graph(sess.graph)
    for i in range(1001):
        sess.run(optimizer, feed_dict={x: train_batch_x, y: train_batch_y})
        avg_cost += sess.run(cross_entropy, feed_dict={x: train_batch_x, y: train_batch_y})
        tf.summary.scalar("avrage cost", avg_cost)
        merged_summary_string = sess.run(merged_summary, feed_dict={x: train_batch_x, y: train_batch_y})
        writer.add_summary(merged_summary_string, i)
        train_accuracy = sess.run(accuracy, feed_dict={x: train_batch_x, y: train_batch_y})
        print("STEP:", i,"=>", train_accuracy,"% accuracy.")
        writer.close()

所以我的问题是：如何修复我的模型来预测X和Y坐标？

感谢您的每一条建议或至少努力！祝你有愉快的一天！

更新：所以我应该更换我的sotfmax功能：

with tf.name_scope("softmax") as scope:
    softmax = tf.nn.softmax(tf.matmul(x, W) + b)

用这个？：

with tf.name_scope("softmax") as scope:
    softmax = tf.nn.softmax_cross_entropy_with_logits()'

但是这个函数的输入是什么？

TensorFlow，预测从rssi输入

0 个答案: