我正在尝试使用深度神经网络架构对二进制标签值进行分类 - 0 和 +1。这是我在 tensorflow 中执行此操作的代码。这个问题也从 previous question 中的讨论中继承
import tensorflow as tf
import numpy as np
from preprocess import create_feature_sets_and_labels
train_x,train_y,test_x,test_y = create_feature_sets_and_labels()
x = tf.placeholder('float', [None, 5])
y = tf.placeholder('float')
n_nodes_hl1 = 500
n_nodes_hl2 = 500
# n_nodes_hl3 = 500
n_classes = 1
batch_size = 100
def neural_network_model(data):
hidden_1_layer = {'weights':tf.Variable(tf.random_normal([5, n_nodes_hl1])),
'biases':tf.Variable(tf.random_normal([n_nodes_hl1]))}
hidden_2_layer = {'weights':tf.Variable(tf.random_normal([n_nodes_hl1, n_nodes_hl2])),
'biases':tf.Variable(tf.random_normal([n_nodes_hl2]))}
# hidden_3_layer = {'weights':tf.Variable(tf.random_normal([n_nodes_hl2, n_nodes_hl3])),
# 'biases':tf.Variable(tf.random_normal([n_nodes_hl3]))}
# output_layer = {'weights':tf.Variable(tf.random_normal([n_nodes_hl3, n_classes])),
# 'biases':tf.Variable(tf.random_normal([n_classes]))}
output_layer = {'weights':tf.Variable(tf.random_normal([n_nodes_hl2, n_classes])),
'biases':tf.Variable(tf.random_normal([n_classes]))}
l1 = tf.add(tf.matmul(data, hidden_1_layer['weights']), hidden_1_layer['biases'])
l1 = tf.nn.relu(l1)
l2 = tf.add(tf.matmul(l1, hidden_2_layer['weights']), hidden_2_layer['biases'])
l2 = tf.nn.relu(l2)
# l3 = tf.add(tf.matmul(l2, hidden_3_layer['weights']), hidden_3_layer['biases'])
# l3 = tf.nn.relu(l3)
# output = tf.transpose(tf.add(tf.matmul(l3, output_layer['weights']), output_layer['biases']))
output = tf.add(tf.matmul(l2, output_layer['weights']), output_layer['biases'])
return output
def train_neural_network(x):
prediction = tf.sigmoid(neural_network_model(x))
cost = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(prediction, y))
optimizer = tf.train.AdamOptimizer().minimize(cost)
hm_epochs = 10
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, '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'))
predicted_class = tf.greater(prediction,0.5)
correct = tf.equal(predicted_class, tf.equal(y,1.0))
accuracy = tf.reduce_mean( tf.cast(correct, 'float') )
# print (test_x.shape)
# accuracy = tf.nn.l2_loss(prediction-y,name="squared_error_test_cost")/test_x.shape[0]
print('Accuracy:', accuracy.eval({x: test_x, y: test_y}))
train_neural_network(x)
具体来说,(继承上一个问题的讨论)我删除了一层 -
hidden_3_layer 。改变了
prediction = neural_network_model(x)
到
prediction = tf.sigmoid(neural_network_model(x))
并根据尼尔的回答添加了
predicted_class, correct, accuracy 部分。我还在我的 csv 中将所有 -1 更改为 0。
这是我的踪迹:
('Epoch', 0, 'completed out of', 10, 'loss:', 37.312037646770477)
('Epoch', 1, 'completed out of', 10, 'loss:', 37.073578298091888)
('Epoch', 2, 'completed out of', 10, 'loss:', 37.035196363925934)
('Epoch', 3, 'completed out of', 10, 'loss:', 37.035196363925934)
('Epoch', 4, 'completed out of', 10, 'loss:', 37.035196363925934)
('Epoch', 5, 'completed out of', 10, 'loss:', 37.035196363925934)
('Epoch', 6, 'completed out of', 10, 'loss:', 37.035196363925934)
('Epoch', 7, 'completed out of', 10, 'loss:', 37.035196363925934)
('Epoch', 8, 'completed out of', 10, 'loss:', 37.035196363925934)
('Epoch', 9, 'completed out of', 10, 'loss:', 37.035196363925934)
('Accuracy:', 0.42608696)
如您所见,损失并没有减少。因此我不知道它是否仍然正常工作。
这是多次重新运行的结果。结果摇摆不定:
('Epoch', 0, 'completed out of', 10, 'loss:', 26.513012945652008)
('Epoch', 1, 'completed out of', 10, 'loss:', 26.513012945652008)
('Epoch', 2, 'completed out of', 10, 'loss:', 26.513012945652008)
('Epoch', 3, 'completed out of', 10, 'loss:', 26.513012945652008)
('Epoch', 4, 'completed out of', 10, 'loss:', 26.513012945652008)
('Epoch', 5, 'completed out of', 10, 'loss:', 26.513012945652008)
('Epoch', 6, 'completed out of', 10, 'loss:', 26.513012945652008)
('Epoch', 7, 'completed out of', 10, 'loss:', 26.513012945652008)
('Epoch', 8, 'completed out of', 10, 'loss:', 26.513012945652008)
('Epoch', 9, 'completed out of', 10, 'loss:', 26.513012945652008)
('Accuracy:', 0.60124224)
其他:
('Epoch', 0, 'completed out of', 10, 'loss:', 22.873702049255371)
('Epoch', 1, 'completed out of', 10, 'loss:', 22.873702049255371)
('Epoch', 2, 'completed out of', 10, 'loss:', 22.873702049255371)
('Epoch', 3, 'completed out of', 10, 'loss:', 22.873702049255371)
('Epoch', 4, 'completed out of', 10, 'loss:', 22.873702049255371)
('Epoch', 5, 'completed out of', 10, 'loss:', 22.873702049255371)
('Epoch', 6, 'completed out of', 10, 'loss:', 22.873702049255371)
('Epoch', 7, 'completed out of', 10, 'loss:', 22.873702049255371)
('Epoch', 8, 'completed out of', 10, 'loss:', 22.873702049255371)
('Epoch', 9, 'completed out of', 10, 'loss:', 22.873702049255371)
('Accuracy:', 1.0)
另一个:
('Epoch', 0, 'completed out of', 10, 'loss:', 23.163824260234833)
('Epoch', 1, 'completed out of', 10, 'loss:', 22.88000351190567)
('Epoch', 2, 'completed out of', 10, 'loss:', 22.873702049255371)
('Epoch', 3, 'completed out of', 10, 'loss:', 22.873702049255371)
('Epoch', 4, 'completed out of', 10, 'loss:', 22.873702049255371)
('Epoch', 5, 'completed out of', 10, 'loss:', 22.873702049255371)
('Epoch', 6, 'completed out of', 10, 'loss:', 22.873702049255371)
('Epoch', 7, 'completed out of', 10, 'loss:', 22.873702049255371)
('Epoch', 8, 'completed out of', 10, 'loss:', 22.873702049255371)
('Epoch', 9, 'completed out of', 10, 'loss:', 22.873702049255371)
('Accuracy:', 0.99627328)
我还看到了 0.0 的准确度值 -_-
---------------编辑---------------
关于数据和数据处理的一些细节。我正在使用来自 Yahoo! 的 IBM 每日股票数据!融资 20 年(几乎)。这相当于大约 5200 行条目。
这是我处理它的方式:
import numpy as np
import pandas as pd
from sklearn.preprocessing import MinMaxScaler
import csv
import pickle
def create_feature_sets_and_labels(test_size = 0.2):
df = pd.read_csv("ibm.csv")
df = df.iloc[::-1]
features = df.values
testing_size = int(test_size*len(features))
train_x = list(features[1:,1:6][:-testing_size])
train_y = list(features[1:,7][:-testing_size])
test_x = list(features[1:,1:6][-testing_size:])
test_y = list(features[1:,7][-testing_size:])
scaler = MinMaxScaler(feature_range=(-5,5))
train_x = scaler.fit_transform(train_x)
train_y = scaler.fit_transform(train_y)
test_x = scaler.fit_transform(test_x)
test_y = scaler.fit_transform(test_y)
return train_x, train_y, test_x, test_y
if __name__ == "__main__":
train_x, train_y, test_x, test_y = create_feature_sets_and_labels()
with open('stockdata.pickle', 'wb') as f:
pickle.dump([train_x, train_y, test_x, test_y], f)
第 0 列是日期。所以这不被用作特征。第 7 列也不是。我使用
sklearn 的
MinMaxScaler() 在 -5 到 5 的范围内对数据进行了标准化。
-------------编辑2-------
我注意到当数据以非标准化形式呈现时,系统不会改变其准确性。
请您参考如下方法:
一旦在 ML 训练任务中将数据预处理为错误的形状或范围,其余的数据流就会出错。您在问题的代码中以不同的方式多次执行此操作。
以事物的顺序进行处理。第一个问题是预处理。你的目标应该是:
.fit_transform因为这重新适合缩放器。 这重写了你的
create_feature_sets_and_labels函数正确地做事:
def create_feature_sets_and_labels(test_size = 0.2):
df = pd.read_csv("ibm.csv")
df = df.iloc[::-1]
features = df.values
testing_size = int(test_size*len(features))
train_x = np.array(features[1:,1:6][:-testing_size]).astype(np.float32)
train_y = np.array(features[1:,7][:-testing_size]).reshape(-1, 1).astype(np.float32)
test_x = np.array(features[1:,1:6][-testing_size:]).astype(np.float32)
test_y = np.array(features[1:,7][-testing_size:]).reshape(-1, 1).astype(np.float32)
scaler = MinMaxScaler(feature_range=(-5,5))
scaler.fit(train_x)
train_x = scaler.transform(train_x)
test_x = scaler.transform(test_x)
return train_x, train_y, test_x, test_y
与您的版本的重要区别:
np.array ,而不是 list (细微差别)[n_examples, n_outputs] (主要区别,你的行向量形状是后来很多问题的原因)您的此数据的训练代码也存在一些问题:
y = tf.placeholder('float')应该是 y = tf.placeholder('float', [None, 1]) .这对处理没有影响,但在 y 时会正确抛出错误。是错误的形状。那个错误会更早地成为事情出错的线索。 n_nodes_hl1 = 500和 n_nodes_hl2 = 500可以低得多,并且网络实际上会更好地工作,例如n_nodes_hl1 = 10和 n_nodes_hl2 = 10 - 这主要是因为您对权重使用了较大的初始值,您也可以缩小权重,而对于更复杂的数据,您可能想要这样做。在这种情况下,减少隐藏神经元的数量会更简单。 output = neural_network_model(x)
prediction = tf.sigmoid(output)
cost = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(output, y))
optimizer = tf.train.AdamOptimizer().minimize(cost)
. . .这是一个主要区别。通过使用
sigmoid_cross_entropy_with_logits您已 promise 使用输出层的预转换值进行训练。但是您仍然希望预测值能够测量准确性(或用于您想要读取预测值的网络的任何其他用途)。 'loss:', epoch_loss/(len(train_x)/batch_size) 如果我进行所有这些更正,然后再运行几个 epoch - 例如50,然后我得到
0.7 的典型损失和
0.5 的准确度度量- 这发生得相当可靠,但由于起始重量的变化确实会移动一点。准确性不是很稳定,并且可能会受到过度拟合的影响,这是您根本不允许的(并且您应该阅读有助于测量和管理过度拟合的技术,这是可靠地训练 NN 的重要部分)
0.5 的值可能看起来很糟糕。可以通过修改网络架构或元参数来改进它。我可以下到
0.43训练损失和高达
0.83测试准确性,例如通过交换
tf.nn.relu对于
tf.tanh在隐藏层中运行 500 个 epoch。
要了解有关神经网络的更多信息、训练时要测量的内容以及模型中可能值得更改的内容,您需要更深入地研究该主题。
