Question

我对tensorflow很新，正在制作我的第一个双层神经网络。我正在利用UCI的心脏病数据集。

import tensorflow as tf
import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split

RANDOM_SEED = 41
tf.set_random_seed(RANDOM_SEED)

def init_weights(shape):
    """ Weight initialization """
    weights = tf.random_normal(shape, stddev=0.1)
    return tf.Variable(weights)

def forwardprop(X, w_1, w_2, w_3):
    h_1   = tf.nn.sigmoid(tf.matmul(X, w_1))
    h_2   = tf.nn.sigmoid(tf.matmul(h_1, w_2))
    yhat = tf.nn.sigmoid(tf.matmul(h_2, w_3))
    return yhat

def get_heart_data():   
    disease = pd.read_csv('../data/disease.csv')

    disease.replace(to_replace="?", value = "u", inplace = True)
    disease = pd.get_dummies(disease, columns=['ca', 'thal', 'fbs', 'exang', 'slop', 'sex', 'cp'], drop_first=True)

    all_X = disease.drop(['pred_attribute'],1)
    all_y = disease['pred_attribute']
    all_y = pd.get_dummies(all_y, columns=['pred_attribute'], drop_first=False)
    return train_test_split(all_X, all_y, test_size=0.3, random_state=RANDOM_SEED)

def main():
    train_X, test_X, train_y, test_y = get_heart_data()

    # Layer's sizes
    x_size = 21
    h_1_size = 154 
    h_2_size = 79  
    y_size = 5

    # Symbols
    X = tf.placeholder("float", shape=[None, x_size])
    y = tf.placeholder("float", shape=[None, y_size])

    # Weight initializations
    w_1 = init_weights((x_size, h_1_size))
    w_2 = init_weights((h_1_size, h_2_size))
    w_3 = init_weights((h_2_size, y_size))

    # Forward propagation
    logits   = forwardprop(X, w_1, w_2, w_3)

    # Backward propagation
    cost    = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y, logits=logits))
    updates = tf.train.GradientDescentOptimizer(0.01).minimize(cost)

    # Run SGD
    sess = tf.Session()
    init = tf.global_variables_initializer()
    sess.run(init)


    for epoch in range(100):
        # Train with each example
        for i in range(len(train_X)):

            sess.run(updates, feed_dict={X: train_X, y: train_y })

        pred = tf.nn.softmax(logits)  # Apply softmax to logits
        correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
        accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
        training_accuracy = sess.run(accuracy, feed_dict={X: train_X, y: train_y})
        testing_accuracy = sess.run(accuracy, feed_dict={X: test_X, y: test_y})
        print("Epoch = %d, train accuracy = %.2f%%, test accuracy = %.2f%%"
          % (epoch + 1, 100 * training_accuracy, 100. * testing_accuracy))

    sess.close()

main()

我认为我已经正确设置了所有内容，但是当我运行该程序时，它反复给我一遍又一遍的相同精度。

Epoch = 1, train accuracy = 55.19%, test accuracy = 51.65%
Epoch = 2, train accuracy = 55.19%, test accuracy = 51.65%
Epoch = 3, train accuracy = 55.19%, test accuracy = 51.65%
Epoch = 4, train accuracy = 55.19%, test accuracy = 51.65%
Epoch = 5, train accuracy = 55.19%, test accuracy = 51.65%
Epoch = 6, train accuracy = 55.19%, test accuracy = 51.65%
Epoch = 7, train accuracy = 55.19%, test accuracy = 51.65%
Epoch = 8, train accuracy = 55.19%, test accuracy = 51.65%
Epoch = 9, train accuracy = 55.19%, test accuracy = 51.65%
Epoch = 10, train accuracy = 55.19%, test accuracy = 51.65%

这一直持续到纪元100.我已经尝试乘以100000以确定它是否只是稍微变化，但每次都保持不变。我不知道这是我的网络还是我的准确性功能还是别的什么非常感谢您的帮助，
- 马特

Answer 1

您的测试和训练集在每个时代保持不变，那么为什么您会期望不同的结果？

我认为你想要的只是从少数几个样本开始，并在时代中添加更多：

n_epoch = 100
# Assuming of course that you have more than n_epoch samples in each of your sets
trainSamplesByEpoch = int(len(train_X) / n_epoch)      
for epoch in range(1,100):
    train_X_current = train_X[0:epoch*trainSamplesByEpoch] 
    train_y_current = train_y[0:epoch*trainSamplesByEpoch] 
    # Train your network with train_X_current, train_y_current 
    # Compute the train accuracy with train_X_current, train_y_current  
    # Compute the test accuracy with test_X, test_y

以这种方式使用时代，以便知道有多少样本足以达到所需的性能。使用所有样本可能会导致过度拟合模型。

Answer 2

一个可能的问题是您构建网络的方式。你到处都在使用非线性，甚至是你的输出层。

您正在使用的损失tf.nn.softmax_cross_entropy_with_logits()要求logits是线性函数。所以这就是构建网络的方式：

def forwardprop(X, w_1, w_2, w_3):
h_1   = tf.nn.sigmoid(tf.matmul(X, w_1))
h_2   = tf.nn.sigmoid(tf.matmul(h_1, w_2))
yhat = tf.matmul(h_2, w_3)
return yhat

当您转向更复杂的网络时，您构建代码的方式也会导致问题。你不应该想到forwardprop()和backprop()。在编写张量流代码时，请将其视为指定图形和必要的计算。请查看tensorflow tutorials，了解如何构建代码的黄金标准。

双层神经网络的准确性没有提高

2 个答案: