直接给出一般的通用编程模型,并通过3个例子来看看使用情况。
#tensorflow编程模型
import tensorflow as tf
# define the training loop operations
def inference(X):
# compute inference model over data X and return the result
return
def loss(X, Y):
# compute loss over training data X and expected values Y
return
def inputs():
# read/generate input training data X and expected outputs Y
return
def train(total_loss):
# train / adjust model parameters according to computed total loss
return
def evaluate(sess, X, Y):
# evaluate the resulting trained model
return
# Launch the graph in a session, setup boilerplate
with tf.Session() as sess:
tf.global_variables_initializer().run()
#tf.initialize_all_variables().run()
X, Y = inputs()
total_loss = loss(X, Y)
train_op = train(total_loss)
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
# actual training loop
training_steps = 1000
for step in range(training_steps):
sess.run([train_op])
# for debugging and learning purposes, see how the loss gets decremented thru training steps
if step % 10 == 0:
print( "loss: ", sess.run([total_loss]))
evaluate(sess, X, Y)
coord.request_stop()
coord.join(threads)
sess.close()
1. 线性回归,用来预测体重年龄与 血脂含量的关系
#Linear Regression
import tensorflow as tf
# Explicitly create a Graph object
W = tf.Variable(tf.zeros([2, 1]), name="weights")
b = tf.Variable(0., name="bias")
# define the training loop operations
def inference(X):
# compute inference model over data X and return the result
return tf.matmul(X,W) + b #矩阵相乘
def loss(X, Y):
# compute loss over training data X and expected values Y
Y_predicted = inference(X)
return tf.reduce_sum(tf.squared_difference(Y,Y_predicted))
def inputs():
# read/generate input training data X and expected outputs Y
weight_age = [[84, 46], [73, 20], [65, 52], [70, 30], [76, 57], [69, 25], [63, 28], [72, 36],[79,51],[75,50],[82,34],[59,46],[67,23],[85,37],[55,40],[63,30]]
blood_fat_content = [354, 190, 405, 263, 451, 302, 288, 385, 402, 365, 209, 290, 346, 254, 395,434,220,374,308,220,311,181,274,303,244]
return tf.to_float(weight_age), tf.to_float(blood_fat_content)
#with GradientDescentOptimizer
def train(total_loss):
learning_rate = 0.0000001
return tf.train.GradientDescentOptimizer(learning_rate).minimize(total_loss)
def evaluate(sess, X, Y):
# evaluate the resulting trained model
print(sess.run(inference([[80., 25.]]))) # ~ 303
print(sess.run(inference([[65., 25.]])))
with tf.Session() as sess:
tf.global_variables_initializer().run()
X, Y = inputs()
print(X)
print(Y)
total_loss = loss(X, Y)
train_op = train(total_loss)
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
#tf.train.start_queue_runners 这个函数将会启动输入管道的线程,填充样本到队列中,
#以便出队操作可以从队列中拿到样本。这种情况下最好配合使用一个tf.train.Coordinator,这样可以在发生错误的情况下正确地关闭这些线程。
#actual training loop
training_steps = 1000
for step in range(training_steps):
sess.run([train_op])
#for debugging and learning purposes, see how the loss gets decremented thru training steps
if step % 10 == 0:
print("loss: ", sess.run([total_loss]))
evaluate(sess, X, Y)
coord.request_stop()
coord.join(threads)
sess.close()
2. 使用逻辑回归LR,本地读取文件数据,然后预测泰坦尼克生存者
import tensorflow as tf
# same params and variables initialization as log reg.
W = tf.Variable(tf.zeros([5, 1]), name="weights")
b = tf.Variable(0., name="bias")
# former inference is now used for combining inputs
def combine_inputs(X):
return tf.matmul(X, W) + b
# new inferred value is the sigmoid applied to the former
def inference(X):
return tf.sigmoid(combine_inputs(X)) #逻辑回归 LR
#calculating cross entropy 交叉熵
def loss(X, Y):
return tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(labels=combine_inputs(X), logits=Y))
def read_csv(batch_size, file_name, record_defaults):
#filename_queue = tf.train.string_input_producer([os.path.dirname(__file__) + "/" + file_name])
filename_queue = tf.train.string_input_producer(["E:\\testData\\taitannike\\" + file_name])
reader = tf.TextLineReader(skip_header_lines=1)
key, value = reader.read(filename_queue)
# decode_csv will convert a Tensor from type string (the text line) in
# a tuple of tensor columns with the specified defaults, which also
# sets the data type for each column
decoded = tf.decode_csv(value, record_defaults=record_defaults)
# batch actually reads the file and loads "batch_size" rows in a single tensor
return tf.train.shuffle_batch(decoded,
batch_size=batch_size,
capacity=batch_size * 50,
min_after_dequeue=batch_size)
def inputs():
passenger_id, survived, pclass, name, sex, age, sibsp, parch, ticket, fare, cabin, embarked =read_csv(100, "train.csv", [[0.0], [0.0], [0], [""], [""], [0.0], [0.0], [0.0], [""], [0.0],[""], [""]])
# convert categorical data
is_first_class = tf.to_float(tf.equal(pclass, [1]))
is_second_class = tf.to_float(tf.equal(pclass, [2]))
is_third_class = tf.to_float(tf.equal(pclass, [3]))
gender = tf.to_float(tf.equal(sex, ["female"]))
# Finally we pack all the features in a single matrix;
# We then transpose to have a matrix with one example per row and one feature per column.
features = tf.transpose(tf.stack([is_first_class, is_second_class, is_third_class, gender, age]))
survived = tf.reshape(survived, [100, 1])
return features, survived
def train(total_loss):
learning_rate = 0.01
return tf.train.GradientDescentOptimizer(learning_rate).minimize(total_loss)
def evaluate(sess, X, Y):
predicted = tf.cast(inference(X) > 0.5, tf.float32)
print(sess.run(tf.reduce_mean(tf.cast(tf.equal(predicted, Y), tf.float32))))
with tf.Session() as sess:
tf.global_variables_initializer().run()
#tf.initialize_all_variables().run()
X, Y = inputs()
total_loss = loss(X, Y)
train_op = train(total_loss)
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
# actual training loop
training_steps = 1000
for step in range(training_steps):
sess.run([train_op])
# for debugging and learning purposes, see how the loss gets decremented thru training steps
if step % 10 == 0:
print("loss: ", sess.run([total_loss]))
evaluate(sess, X, Y)
coord.request_stop()
coord.join(threads)
sess.close()
3. 使用softmax的分类,对水仙花数据分类
#softmax C-classify ,Iris-data
import tensorflow as tf
# this time weights form a matrix, not a column vector, one "weight vector" per class.
W = tf.Variable(tf.zeros([4, 3]), name="weights")
# so do the biases, one per class.
b = tf.Variable(tf.zeros([3], name="bias"))
# former inference is now used for combining inputs
def combine_inputs(X):
return tf.matmul(X, W) + b
def inference(X):
return tf.nn.softmax(combine_inputs(X))
def loss(X, Y):
return tf.reduce_mean(tf.nn.sparse_softmax_cross_entropy_with_logits(labels=Y, logits=combine_inputs(X)))
def read_csv(batch_size, file_name, record_defaults):
filename_queue = tf.train.string_input_producer(["E:\\testData\\taitannike\\" + file_name])
#filename_queue = tf.train.string_input_producer([os.path.dirname(__file__) + "/" + file_name])
reader = tf.TextLineReader(skip_header_lines=1)
key, value = reader.read(filename_queue)
# decode_csv will convert a Tensor from type string (the text line) in
# a tuple of tensor columns with the specified defaults, which also
# sets the data type for each column
decoded = tf.decode_csv(value, record_defaults=record_defaults)
# batch actually reads the file and loads "batch_size" rows in a single tensor
return tf.train.shuffle_batch(decoded,
batch_size=batch_size,
capacity=batch_size * 50,
min_after_dequeue=batch_size)
def inputs():
sepal_length, sepal_width, petal_length, petal_width, label =\
read_csv(100, "iris.data", [[0.0], [0.0], [0.0], [0.0], [""]])
# convert class names to a 0 based class index.
label_number = tf.to_int32(tf.argmax(tf.to_int32(tf.stack([
tf.equal(label, ["Iris-setosa"]),
tf.equal(label, ["Iris-versicolor"]),
tf.equal(label, ["Iris-virginica"])
])), 0))
# Pack all the features that we care about in a single matrix;
# We then transpose to have a matrix with one example per row and one feature per column.
features = tf.transpose(tf.stack([sepal_length, sepal_width, petal_length, petal_width]))
return features, label_number
def train(total_loss):
learning_rate = 0.01
return tf.train.GradientDescentOptimizer(learning_rate).minimize(total_loss)
def evaluate(sess, X, Y):
predicted = tf.cast(tf.arg_max(inference(X), 1), tf.int32)
print(sess.run(tf.reduce_mean(tf.cast(tf.equal(predicted, Y), tf.float32))))
# Launch the graph in a session, setup boilerplate
with tf.Session() as sess:
tf.global_variables_initializer().run()
#tf.initialize_all_variables().run()
X, Y = inputs()
total_loss = loss(X, Y)
train_op = train(total_loss)
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
# actual training loop
training_steps = 10000
for step in range(training_steps):
sess.run([train_op])
# for debugging and learning purposes, see how the loss gets decremented thru training steps
if step % 10 == 0:
print("loss: ", sess.run([total_loss]))
evaluate(sess, X, Y)
coord.request_stop()
coord.join(threads)
sess.close()