权重和偏差在张量流中不更新 [英] Weights and Biases not updating in tensorflow

问题描述

我已经建立了这个神经网络，以判断房屋是好货还是坏货.由于某些原因，代码没有更新权重和偏差.我的损失保持不变.这是我的代码:

I've made this neural net to figure out whether a house is a good buy or a bad buy. For some reasons the code is not updating weights and biases. My loss stays same. This is my code:

我已经建立了这个神经网络，以判断房屋是好货还是坏货.由于某些原因，代码没有更新权重和偏差.我的损失保持不变.这是我的代码:

I've made this neural net to figure out whether a house is a good buy or a bad buy. For some reasons the code is not updating weights and biases. My loss stays same. This is my code:

import pandas as pd
import tensorflow as tf

data = pd.read_csv("E:/workspace_py/datasets/good_bad_buy.csv")

features = data.drop(['index', 'good buy'], axis = 1)
lbls = data.drop(['index', 'area', 'bathrooms', 'price', 'sq_price'], axis = 1)

features = features[0:20]
lbls = lbls[0:20]

print(features)
print(lbls)
n_examples = len(lbls)

# Model

# Hyper parameters

epochs = 100
learning_rate = 0.1
batch_size = 1

input_data = tf.placeholder('float', [None, 4])
labels = tf.placeholder('float', [None, 1])

weights = {
            'hl1': tf.Variable(tf.random_normal([4, 10])),
            'hl2': tf.Variable(tf.random_normal([10, 10])),
            'hl3': tf.Variable(tf.random_normal([10, 4])),
            'ol': tf.Variable(tf.random_normal([4, 1]))
            }

biases = {
            'hl1': tf.Variable(tf.random_normal([10])),
            'hl2': tf.Variable(tf.random_normal([10])),
            'hl3': tf.Variable(tf.random_normal([4])),
            'ol': tf.Variable(tf.random_normal([1]))
            }

hl1 = tf.nn.relu(tf.add(tf.matmul(input_data, weights['hl1']), biases['hl1']))
hl2 = tf.nn.relu(tf.add(tf.matmul(hl1, weights['hl2']), biases['hl2']))
hl3 = tf.nn.relu(tf.add(tf.matmul(hl2, weights['hl3']), biases['hl3']))
ol = tf.nn.sigmoid(tf.add(tf.matmul(hl3, weights['ol']), biases['ol']))

loss = tf.reduce_mean((labels - ol)**2)
train = tf.train.AdamOptimizer(learning_rate).minimize(loss)

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

iterations = int(n_examples/batch_size)


for epoch_no in range(epochs):
    ptr = 0
    for iteration_no in range(iterations):
        epoch_input = features[ptr:ptr+batch_size]
        epoch_label = lbls[ptr: ptr+batch_size]
        ptr = ptr + batch_size
        _, err = sess.run([train, loss], feed_dict={input_data: features, labels: lbls})
    print("Error at epoch ", epoch_no, ": ", err)

print(sess.run(ol, feed_dict={input_data: [[2104, 3, 399900, 190.0665]]}))

这是数据集:

Features:

    area  bathrooms   price    sq_price
0   2104          3  399900  190.066540
1   1600          3  329900  206.187500
2   2400          3  369000  153.750000
3   1416          2  232000  163.841808
4   3000          4  539900  179.966667
5   1985          4  299900  151.083123
6   1534          3  314900  205.280313
7   1427          3  198999  139.452698
8   1380          3  212000  153.623188
9   1494          3  242500  162.315930
10  1940          4  239999  123.710825
11  2000          3  347000  173.500000
12  1890          3  329999  174.602645
13  4478          5  699900  156.297454
14  1268          3  259900  204.968454
15  2300          4  449900  195.608696
16  1320          2  299900  227.196970
17  1236          3  199900  161.731392
18  2609          4  499998  191.643542
19  3031          4  599000  197.624546

labels:

    good buy
0        1.0
1        0.0
2        1.0
3        0.0
4        1.0
5        0.0
6        0.0
7        1.0
8        0.0
9        0.0
10       1.0
11       1.0
12       1.0
13       1.0
14       0.0
15       1.0
16       0.0
17       1.0
18       1.0
19       1.0

有关如何解决此问题的任何建议?我尝试过tf.reduce_mean以外的tf.reduce_sum.我还尝试了更大的batch_size.

Any suggestions on how to fix this? I've tried tf.reduce_sum other than tf.reduce_mean. I've also tried a larger batch_size.

推荐答案

需要考虑的几件事

• 无法正确评估Minibatch，因为您输入了功能和lbls而不是epoch_input和epoch_label.
• 您不会以任何方式对数据进行预处理，因此它完全超出范围. IE.我下面的代码将功能标准化为stddev和mean.您可能会考虑使用batch_normalization.
• 您在任何时候都不会评估错误.您需要一套训练有素的测试仪.我下面的代码没有提供数据，但是它会根据错误％进行测试，而不仅仅是损失(这是错误的弱代理，因此您不应将其称为错误).
• 您可以初始化对随机法线的偏见.您可能只想从零开始.
• 您可能应该使用tf.layers或其他高级api.

以下代码实现了95％的训练错误.您想要使用未用于训练来评估测试错误的保留数据集进行测试.

The below code achieves a training error of 95%. You'd want to test with a held out data set not used for training to evaluate the testing error.

#!/usr/bin/env python
import sys
import pandas as pd
import numpy as np
import tensorflow as tf


data = pd.read_csv("data.csv")

features = data.drop(['good buy'], axis = 1)
lbls = data.drop([ 'area', 'bathrooms', 'price', 'sq_price'], axis = 1)

features = features[0:20]
lbls = lbls[0:20]

mu = np.mean(features, axis=0)
sigma = (np.std(features, axis=0))
features = (features - mu) / sigma

n_examples = len(lbls)

# Model

# Hyper parameters

epochs = 100
learning_rate = 0.01
batch_size = 5

input_data = tf.placeholder('float', [None, 4])
labels = tf.placeholder('float', [None, 1])

weights = {
      'hl1': tf.Variable(tf.random_normal([4, 10])),
      'hl2': tf.Variable(tf.random_normal([10, 10])),
      'hl3': tf.Variable(tf.random_normal([10, 4])),
      'ol': tf.Variable(tf.random_normal([4, 1]))
      }

biases = {
      'hl1': tf.Variable(tf.zeros([10])),
      'hl2': tf.Variable(tf.zeros([10])),
      'hl3': tf.Variable(tf.zeros([4])),
      'ol': tf.Variable(tf.zeros([1]))
      }



hl1 = tf.nn.relu(tf.add(tf.matmul(input_data, weights['hl1']), biases['hl1']))
hl2 = tf.nn.relu(tf.add(tf.matmul(hl1, weights['hl2']), biases['hl2']))
hl3 = tf.nn.relu(tf.add(tf.matmul(hl2, weights['hl3']), biases['hl3']))
ol = tf.nn.sigmoid(tf.add(tf.matmul(hl3, weights['ol']), biases['ol']))

loss = tf.reduce_mean((labels - ol)**2)
train = tf.train.AdamOptimizer(learning_rate).minimize(loss)

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

iterations = int(n_examples/batch_size)


def training_accuracy():
  foo,  = sess.run([ol], feed_dict={input_data: features, labels: lbls})
  return (float(np.count_nonzero(np.equal(np.round(foo), lbls))) / float(lbls.shape[0]))


print("Initial training accuracy %f" % training_accuracy())


for epoch_no in range(epochs):
  ptr = 0
  for iteration_no in range(iterations):
    epoch_input = features[ptr:ptr+batch_size]
    epoch_label = lbls[ptr: ptr+batch_size]
    ptr = (ptr + batch_size)%len(features)
    _, err = sess.run([train, loss], feed_dict={input_data: epoch_input, labels: epoch_label})
  print("Error at epoch ", epoch_no, ": ", err)
  print("  Training accuracy %f" % training_accuracy())

另外，请不要在github上发布这样的使用问题，它们属于StackOverflow.

Also, please do not post usage questions like this on github, they belong here on StackOverflow.

这篇关于权重和偏差在张量流中不更新的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！