TensorFlow 提供的示例对于入门来说有点复杂，所以我尝试教 TensorFlow 训练一个神经网络来预测三个二进制数字的和。网络将其中两个作为输入；第三个是未知的。因此，“最佳”网络会猜测总和将是两个已知位的总和，再加上未知位的 1/2。假设“损失”函数是网络预测值与实际值之差的平方。
我已经编写了生成试验的代码:
import tensorflow as tf
import numpy as np
from random import randint
flags = tf.app.flags
FLAGS = flags.FLAGS
flags.DEFINE_integer('batch_size', 5, 'Batch size. ')
flags.DEFINE_float('learning_rate', 0.01, 'Initial learning rate.')
flags.DEFINE_integer('dim1', 3, 'layer size')
flags.DEFINE_integer('training_epochs', 10, 'Number of passes through the main training loop')
def ezString(list):
#debugging code so I can see what is going on
listLength = len(list)
r = ''
for i in range(listLength):
value = list[i]
valueString = str(value)
r = r + ' '
r = r + valueString
return r
def generateTrial():
inputs = np.zeros(2, dtype=np.int)
for i in range(2):
inputs[i] = randint(0,1)
unknownInput = randint(0,1)
sum = 0
for j in range(2):
sum = sum + inputs[j]
sum = sum + unknownInput
inputTensor = tf.pack(inputs)
print 'inputs' + ezString(inputs)
print 'unknown ' + str(unknownInput)
print 'sum ' + str(sum)
print ''
return inputTensor, sum
def printTensor(tensor):
sh = tensor.get_shape()
print(sh)
def placeholder_inputs(size):
output_placeholder = tf.placeholder(tf.int32, shape=(size))
input_placeholder = tf.placeholder(tf.int32, shape=(size,
2))
return input_placeholder, output_placeholder
def fill_feed_dict(inputs_pl, output_pl):
print ('Filling feed dict')
inputs_placeholder, output_placeholder = placeholder_inputs(FLAGS.batch_size)
inputs = []
outputs = []
for i in range(FLAGS.batch_size):
input, output = generateTrial()
inputTensor = tf.pack(input)
inputs.append(input)
outputs.append(output)
inputs_placeholder = tf.pack(inputs)
outputs_placeholder = tf.pack(outputs)
def run_training():
input_placeholder, output_placeholder = placeholder_inputs(FLAGS.batch_size)
fill_feed_dict(input_placeholder, output_placeholder)
printTensor(input_placeholder)
printTensor(output_placeholder)
run_training()
输出表明这是有效的:
Filling feed dict
inputs 1 0
unknown 0
sum 1
inputs 1 0
unknown 1
sum 2
inputs 0 1
unknown 1
sum 2
inputs 0 1
unknown 0
sum 1
inputs 0 0
unknown 0
sum 0
(5, 2)
(5,)
但我不清楚我将如何完成它。特别是，我需要定义一个损失函数，我还需要将它们连接起来，以便我的网络的输出用于为进一步的训练步骤生成猜测。谁能帮忙？
请您参考如下方法:
我不确定这段代码是否是您想要的，但无论如何我希望您会发现它有用。均方误差实际上随着迭代次数的增加而减少，尽管我还没有测试它来进行预测，所以这取决于你!
import tensorflow as tf
import numpy as np
from random import randint
flags = tf.app.flags
FLAGS = flags.FLAGS
flags.DEFINE_integer('batch_size', 50, 'Batch size.')
flags.DEFINE_float('learning_rate', 0.01, 'Initial learning rate.')
flags.DEFINE_integer('dim1', 3, 'layer size')
flags.DEFINE_integer('training_epochs', 10, 'Number of passes through the main training loop')
flag.DEFINE_integer('num_iters', 100, 'Number of iterations')
def ezString(list):
#debugging code so I can see what is going on
listLength = len(list)
r = ''
for i in range(listLength):
value = list[i]
valueString = str(value)
r = r + ' '
r = r + valueString
return r
def generateTrial():
inputs = np.zeros(2, dtype = np.float)
for i in range(2):
inputs[i] = randint(0, 1)
unknownInput = randint(0, 1)
um = 0
for j in range(2):
sum = sum + inputs[j]
sum = sum + unknownInput
inputTensor = np.asarray(inputs)
return inputTensor, sum
def printTensor(tensor):
sh = tensor.get_shape()
print(sh)
def placeholder_inputs(size):
output_placeholder = tf.placeholder(tf.float32, shape=(size))
input_placeholder = tf.placeholder(tf.float32, shape=(size, 2))
return input_placeholder, output_placeholder
def fill_feed_dict(inputs_pl, output_pl):
inputs = []
outputs = []
for i in range(FLAGS.batch_size):
input, output = generateTrial()
inputs.append(input)
outputs.append(output)
return {inputs_pl: inputs, output_pl: outputs}
def loss(y, pred):
return tf.reduce_mean(tf.pow(y - pred, 2))
def NN(x, y, W1, b1, W2, b2):
layer1 = tf.add(tf.matmul(x, W1), b1)
layer1 = tf.nn.relu(layer1)
output = tf.add(tf.matmul(layer1, W2), b2)
return output, loss(y, output)
def get_params(dim_hidden):
with tf.variable_scope('nn_params'):
return tf.Variable(tf.truncated_normal([2, dim_hidden], stddev = 0.05)), tf.Variable(0.0, (dim_hidden)),\
tf.Variable(tf.truncated_normal([dim_hidden, 1], stddev = 0.05)), tf.Variable(0.0, 1)
def run_training():
input_placeholder, output_placeholder = placeholder_inputs(FLAGS.batch_size)
W1, b1, W2, b2 = get_params(FLAGS.dim1)
pred, loss = NN(input_placeholder, output_placeholder, W1, b1, W2, b2)
optm = tf.train.AdamOptimizer(FLAGS.learning_rate).minimize(loss)
init = tf.initialize_all_variables()
sess = tf.Session()
sess.run(init)
for iters in range(FLAGS.num_iters):
l, _ = sess.run([loss, optm], feed_dict = fill_feed_dict(input_placeholder, output_placeholder))
print l, iters + 1
