def train():
with tf.Graph().as_default():
global_step = tf.Variable(0,trainable=False)
images,labels = cifar10.distorted_inputs()
logits = cifar10.inference(images)
loss = cifar10.loss(logits,labels)
train_op = cifar10.train(loss,global_step)
saver = tf.train.Saver(tf.all_variables())
summary_op = tf.summary.merge_all()
init = tf.global_variables_initializer()
sess = tf.Session(config=tf.ConfigProto(
log_device_placement = FLAGS.log_device_placement))
sess.run(init)
#
tf.train.start_queue_runners(sess=sess)
summary_writer = tf.summary.FileWriter(FLAGS.train_dir,graph_def=sess.graph_def)
for step in range(FLAGS.max_steps):
start_time = time.time()
_,loss_value = sess.run([train_op,loss])
duration = time.time() - start_time
assert not np.isnan(loss_value), 'Model diverged with loss = NaN'
if step % 10 ==0:
num_examples_per_step = FLAGS.batch_size
examples_per_sec = num_examples_per_step / duration
sec_per_batch = float(duration)
format_str = ('%s: step %d, loss = %.2f (%.1f examples/sec; %.3f '
'sec/batch)')
print(format_str % (datetime.now(), step, loss_value,
examples_per_sec, sec_per_batch))
if step % 100 == 0:
summary_str = sess.run(summary_op)
summary_writer.add_summary(summary_str, step)
if step % 1000 == 0 or (step + 1) == FLAGS.max_steps:
checkpoint_path = os.path.join(FLAGS.train_dir, 'model.ckpt')
saver.save(sess, checkpoint_path, global_step=step)
use_mini_batch=True)
# 构建 KMeans 的图
training_graph = kmeans.training_graph()
if len(training_graph) > 6:
(all_scores, cluster_idx, scores, cluster_centers_initialized,
cluster_centers_var, init_op, train_op) = training_graph
else:
(all_scores, cluster_idx, scores, cluster_centers_initialized,
cluster_centers_var, init_op, train_op) = training_graph
cluster_idx = cluster_idx[0]
avg_distance = tf.reduce_mean(scores)
init_vars = tf.global_variables_initializer()
sess = tf.Session()
sess.run(init_vars, feed_dict={X: full_data_x})
sess.run(init_op, feed_dict={X: full_data_x})
# training
for i in range(1, num_steps + 1):
_, d, idx = sess.run([train_op, avg_distance, cluster_idx],
feed_dict={X: full_data_x})
if i % 10 == 0 or i == 1:
print("Step %i, Avg Distance: %f" % (i, d))
# 为质心分配标签
# 使用每次训练的标签，汇总每个质心的所有标签总数
def word2vec_basic(log_dir):
# 创建tensorboard的可视化目录
if not os.path.exists(log_dir):
os.makedirs(log_dir)
# 第一步，下载数据
url = 'http://mattmahoney.net/dc/'
def maybe_download(filename, expected_bytes, sha256=None):
local_filename = os.path.join(gettempdir(), filename)
if not os.path.exists(local_filename):
local_filename, _ = urllib.request.urlretrieve(
url + filename, local_filename)
statinfo = os.stat(local_filename)
if sha256 and _hash_file(local_filename) != sha256:
raise Exception('Failed to verify ' + local_filename +
' due to hash '
'mismatch. Can you get to it with a browser?')
if statinfo.st_size == expected_bytes:
print("found and verified", filename)
else:
print(statinfo.st_size)
raise Exception('Failed to verify ' + local_filename +
'. Can you get to it with a browser?')
return local_filename
filename = maybe_download(
'text8.zip',
31344016,
sha256=
'a6640522afe85d1963ad56c05b0ede0a0c000dddc9671758a6cc09b7a38e5232')
# 数据转为List<String>
def read_data(filename):
with zipfile.ZipFile(filename) as f:
data = tf.compat.as_str(f.read(f.namelist()[0])).split()
return data
vocabulary = read_data(filename)
print('data_size', len(vocabulary))
# 第二步，建词典并且把罕见词替换成UNK
vocabulary_size = 50000
def build_dataset(words, n_words):
count = [['UNK', -1]]
count.extend(collections.Counter(words).most_common(n_words - 1))
dictionary = {word: index for index, (word, _) in enumerate(count)}
data = []
unk_count = 0
for word in words:
index = dictionary.get(word, 0)
if index == 0: # dictionary['UNK']
unk_count += 1
data.append(index)
count[0][1] = unk_count
reversed_dictionary = dict(zip(dictionary.values(), dictionary.keys()))
return data, count, dictionary, reversed_dictionary
# data: 词表中的所有的词的id
# count： 单词和出现次数的map
# dictionary： 单词-->index 的映射
# reverse_dictionary:index -->单词
data, count, dictionary, reversed_dictionary = build_dataset(
vocabulary, vocabulary_size)
del vocabulary
print('Most common words (+UNK)', count[:5])
print('Sample data', data[:10],
[reversed_dictionary[i] for i in data[:10]])
# 针对skip-gram模型生成batch数据
def generate_batch(batch_size, num_skips, skip_window):
global data_index
assert batch_size % num_skips == 0
assert num_skips <= 2 * skip_window
batch = np.ndarray(shape=(batch_size), dtype=np.int32)
labels = np.ndarray(shape=(batch_size, 1), dtype=np.int32)
# skip的范围
span = 2 * skip_window + 1
buffer = collections.deque(maxlen=span)
if data_index + span > len(data):
data_index = 0
buffer.extend(data[data_index:data_index + span]) # 向后取一个窗口内的结果
data_index += span
for i in range(batch_size // num_skips):
context_words = [w for w in range(span) if w != skip_window]
words_to_use = random.sample(context_words, num_skips)
for j, context_words in enumerate(words_to_use):
batch[i * num_skips + j] = buffer[skip_window]
labels[i * num_skips + j, 0] = buffer[context_words]
if data_index == len(data):
buffer.extend(data[0:span])
data_index = span
else:
buffer.append(data[data_index])
data_index += 1
# Backtrack a little bit to avoid skipping words in the end of a batch
data_index = (data_index - span) % len(data)
return batch, labels
batch, labels = generate_batch(batch_size=8, num_skips=2, skip_window=1)
for i in range(8):
print(batch[i], reversed_dictionary[batch[i]], '->', labels[i, 0],
reversed_dictionary[labels[i, 0]])
# 建立并且训练模型
batch_size = 128
embedding_size = 128 # 词向量维度
skip_window = 1 # 考虑左右几个单词
num_skips = 2 # 复用输入生成标签的次数
num_sampled = 64 # 负样本数量
# 采样一个样本的近邻作为随机验证机，将验证集样本限制为 较低id的单词，是比较高频的构造词汇
# 这三个变量用作显示模型准确率，不影响计算。
valid_size = 16 # 用于评估相似性的随机单词集合
valid_window = 100 #
valid_examples = np.random.choice(valid_window, valid_size, replace=False)
graph = tf.Graph()
with graph.as_default():
# 输入数据
with tf.name_scope('input'):
train_inputs = tf.placeholder(tf.int32, shape=[batch_size])
train_labels = tf.placeholder(tf.int32, shape=[batch_size, 1])
valid_dataset = tf.constant(valid_examples, dtype=tf.int32)
# 操作op和变量variables 固定在CPU上。
with tf.device('/cpu:0'):
with tf.name_scope('embeddings'):
embeddings = tf.Variable(
tf.random_uniform([vocabulary_size, embedding_size], -1.0,
1.0))
embed = tf.nn.embedding_lookup(embeddings, train_inputs)
# 构造NCE损失的变量
with tf.name_scope('weights'):
nce_weights = tf.Variable(
tf.truncated_normal([vocabulary_size, embedding_size],
stddev=1.0 /
math.sqrt(embedding_size)))
with tf.name_scope('biases'):
nce_biases = tf.Variable(tf.zeros([vocabulary_size]))
# 计算该批次的平均nce损失，当评估损失的时候，自动绘制一个新的负样本。
with tf.name_scope('loss'):
loss = tf.reduce_mean(
tf.nn.nce_loss(weights=nce_weights,
biases=nce_biases,
labels=train_labels,
inputs=embed,
num_sampled=num_sampled,
num_classes=vocabulary_size))
# 汇总损失
tf.summary.scalar('loss', loss)
# 构造SGD
with tf.name_scope('opytimizer'):
optimizer = tf.train.GradientDescentOptimizer(1.0).minimize(loss)
# 计算小批次样本和所有样本之间的余弦相似度
norm = tf.sqrt(tf.reduce_sum(tf.square(embeddings), 1, keep_dims=True))
normalized_embeddings = embeddings / norm
valid_embeddings = tf.nn.embedding_lookup(normalized_embeddings,
valid_dataset)
similarity = tf.matmul(valid_embeddings,
normalized_embeddings,
transpose_b=True)
# merge all summary
merged = tf.summary.merge_all()
init = tf.global_variables_initializer()
saver = tf.train.Saver()
# 开始训练
num_steps = 1000001
with tf.compat.v1.Session(graph=graph) as session:
# 写入摘要
writer = tf.summary.FileWriter(log_dir, session.graph)
init.run()
print('inited..')
average_loss = 0
for step in range(num_steps):
batch_inputs, batch_labels = generate_batch(
batch_size, num_skips, skip_window)
feed_dict = {
train_inputs: batch_inputs,
train_labels: batch_labels
}
# 定义元变量
run_metadata = tf.RunMetadata()
_, summary, loss_val = session.run([optimizer, merged, loss],
feed_dict=feed_dict,
run_metadata=run_metadata)
average_loss += loss_val
writer.add_summary(summary, step)
if step == (num_steps - 1):
writer.add_run_metadata(run_metadata, 'step%d' % step)
if step % 2000 == 0:
if step > 0:
average_loss /= 2000
# 平均损失是对最近的2000个批次样本的估计。
print('Average loss at step ', step, ': ', average_loss)
average_loss = 0
if step % 10000 == 0:
sim = similarity.eval()
for i in range(valid_size):
valid_word = reversed_dictionary[valid_examples[i]]
top_k = 8
nearest = (-sim[i, :]).argsort()[1:top_k + 1]
log_str = 'Nearest to %s:' % valid_word
print(
log_str, ', '.join([
reversed_dictionary[nearest[k]]
for k in range(top_k)
]))
final_embeddings = normalized_embeddings.eval()
# 写下embedding的相应标签
with open(log_dir + '/metadata.tsv', 'w') as f:
for i in range(vocabulary_size):
f.write(reversed_dictionary[i] + '\n')
# 保存checkpoint
saver.save(session, os.path.join(log_dir, 'model.ckpt'))
# 配置Tensorboard
config = projector.ProjectorConfig()
embedding_conf = config.embeddings.add()
embedding_conf.tensor_name = embeddings.name
embedding_conf.metadata_path = os.path.join(log_dir, 'metadata.tsv')
projector.visualize_embeddings(writer, config)
writer.close()
# Step 6: Visualize the embeddings.
# pylint: disable=missing-docstring
# Function to draw visualization of distance between embeddings.
def plot_with_labels(low_dim_embs, labels, filename):
assert low_dim_embs.shape[0] >= len(
labels), 'More labels than embeddings'
plt.figure(figsize=(18, 18)) # in inches
for i, label in enumerate(labels):
x, y = low_dim_embs[i, :]
plt.scatter(x, y)
plt.annotate(label,
xy=(x, y),
xytext=(5, 2),
textcoords='offset points',
ha='right',
va='bottom')
plt.savefig(filename)
try:
# pylint: disable=g-import-not-at-top
from sklearn.manifold import TSNE
import matplotlib.pyplot as plt
tsne = TSNE(perplexity=30,
n_components=2,
init='pca',
n_iter=5000,
method='exact')
plot_only = 500
low_dim_embs = tsne.fit_transform(final_embeddings[:plot_only, :])
labels = [reversed_dictionary[i] for i in xrange(plot_only)]
plot_with_labels(low_dim_embs, labels,
os.path.join(gettempdir(), 'tsne.png'))
except ImportError as ex:
print(
'Please install sklearn, matplotlib, and scipy to show embeddings.'
)
print(ex)
sess = tf.InteractiveSession()
# 该函数可以更加灵活的构建代码，可以在运行计算的图的时候通过operation操作插入一些计算图。
x = tf.placeholder("float", shape=[None, 784])
y_ = tf.placeholder("float", shape=[None, 10]) # 占位符
W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10])) # 变量，跟占位符一样作为额外的输入量
sess.run(tf.initialize_all_variables())
y = tf.nn.softmax(tf.matmul(x, W) + b) # 使用softmax计算每个分类的概率
cross_entropy = -tf.reduce_sum(y_ * tf.log(y)) # 交叉熵
train_step = tf.train.GradientDescentOptimizer(0.01).minimize(
cross_entropy) # 训练使用最小梯度下降，且最小化交叉熵loss
init = tf.global_variables_initializer()
for i in range(1000):
batch = mnist.train.next_batch(50) # load mini-batchsize dataset
train_step.run(feed_dict={x: batch[0], y_: batch[1]})
print("训练结束..")
"""
这段表达特别好：tf.argmax 是一个非常有用的函数，它能给出某个tensor对象在某一维上的其数据最大值所在的索引值。
由于标签向量是由0,1组成，因此最大值1所在的索引位置就是类别标签，比如tf.argmax(y,1)返回的是模型对于任一输入x预测到的标签值，
而 tf.argmax(y_,1) 代表正确的标签，我们可以用 tf.equal 来检测我们的预测是否真实标签匹配(索引位置一样表示匹配)。
"""
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
accuarcy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
print(accuarcy.eval(feed_dict={
x: mnist.test.images,
y_: mnist.test.labels
def run_training():
"""Train MNIST for a number of steps."""
# Get the sets of images and labels for training, validation, and
# test on MNIST.
# 加载训练数据，(data_set.train 图像和标签 data_sets.validation 图像和标签，迭代验证 )
data_sets = input_data.read_data_sets(FLAGS.input_data_dir, FLAGS.fake_data)
# Tell TensorFlow that the model will be built into the default Graph.
with tf.Graph().as_default():
# Generate placeholders for the images and labels.
images_placeholder, labels_placeholder = placeholder_inputs(
FLAGS.batch_size)
# Build a Graph that computes predictions from the inference model.
logits = mnist.inference(images_placeholder,
FLAGS.hidden1,
FLAGS.hidden2)
# Add to the Graph the Ops for loss calculation.
loss = mnist.loss(logits, labels_placeholder)
# Add to the Graph the Ops that calculate and apply gradients.
train_op = mnist.training(loss, FLAGS.learning_rate)
# Add the Op to compare the logits to the labels during evaluation.
eval_correct = mnist.evaluation(logits, labels_placeholder)
# Build the summary Tensor based on the TF collection of Summaries.
summary = tf.summary.merge_all()
# Add the variable initializer Op.
init = tf.global_variables_initializer()
# Create a saver for writing training checkpoints.
saver = tf.train.Saver()
# Create a session for running Ops on the Graph.
sess = tf.Session()
# Instantiate a SummaryWriter to output summaries and the Graph.
summary_writer = tf.summary.FileWriter(FLAGS.log_dir, sess.graph)
# And then after everything is built:
# Run the Op to initialize the variables.
sess.run(init)
# Start the training loop.
for step in xrange(FLAGS.max_steps):
start_time = time.time()
# Fill a feed dictionary with the actual set of images and labels
# for this particular training step.
feed_dict = fill_feed_dict(data_sets.train,
images_placeholder,
labels_placeholder)
# Run one step of the model. The return values are the activations
# from the `train_op` (which is discarded) and the `loss` Op. To
# inspect the values of your Ops or variables, you may include them
# in the list passed to sess.run() and the value tensors will be
# returned in the tuple from the call.
_, loss_value = sess.run([train_op, loss],
feed_dict=feed_dict)
duration = time.time() - start_time
# Write the summaries and print an overview fairly often.
if step % 100 == 0:
# Print status to stdout.
print('Step %d: loss = %.2f (%.3f sec)' % (step, loss_value, duration))
# Update the events file.
summary_str = sess.run(summary, feed_dict=feed_dict)
summary_writer.add_summary(summary_str, step)
summary_writer.flush()
# Save a checkpoint and evaluate the model periodically.
if (step + 1) % 1000 == 0 or (step + 1) == FLAGS.max_steps:
checkpoint_file = os.path.join(FLAGS.log_dir, 'model.ckpt')
saver.save(sess, checkpoint_file, global_step=step)
# Evaluate against the training set.
print('Training Data Eval:')
do_eval(sess,
eval_correct,
images_placeholder,
labels_placeholder,
data_sets.train)
# Evaluate against the validation set.
print('Validation Data Eval:')
do_eval(sess,
eval_correct,
images_placeholder,
labels_placeholder,
data_sets.validation)
# Evaluate against the test set.
print('Test Data Eval:')
do_eval(sess,
eval_correct,
images_placeholder,
labels_placeholder,
data_sets.test)