TensorFlow高级API(tf.contrib.learn)及可视化工具TensorBoard的使用

一.TensorFlow高层次机器学习API (tf.contrib.learn)

1.tf.contrib.learn.datasets.base.load_csv_with_header 加载csv格式数据

2.tf.contrib.learn.DNNClassifier 建立DNN模型(classifier)

3.classifer.fit 训练模型

4.classifier.evaluate 评价模型

5.classifier.predict 预测新样本

完整代码：

 from __future__ import absolute_import
 from __future__ import division
 from __future__ import print_function

 import tensorflow as tf
 import numpy as np

 # Data sets
 IRIS_TRAINING = "iris_training.csv"
 IRIS_TEST = "iris_test.csv"

 # Load datasets.
 training_set = tf.contrib.learn.datasets.base.load_csv_with_header(
     filename=IRIS_TRAINING,
     target_dtype=np.int,
     features_dtype=np.float32)
 test_set = tf.contrib.learn.datasets.base.load_csv_with_header(
     filename=IRIS_TEST,
     target_dtype=np.int,
     features_dtype=np.float32)

 # Specify that all features have real-value data
 feature_columns = [tf.contrib.layers.real_valued_column("", dimension=4)]

 # Build 3 layer DNN with 10, 20, 10 units respectively.
 classifier = tf.contrib.learn.DNNClassifier(feature_columns=feature_columns,
                                             hidden_units=[10, 20, 10],
                                             n_classes=3,
                                             model_dir="/tmp/iris_model")

 # Fit model.
 classifier.fit(x=training_set.data,
                y=training_set.target,
                steps=2000)

 # Evaluate accuracy.
 accuracy_score = classifier.evaluate(x=test_set.data,
                                      y=test_set.target)["accuracy"]
 print('Accuracy: {0:f}'.format(accuracy_score))

 # Classify two new flower samples.
 new_samples = np.array(
     [[6.4, 3.2, 4.5, 1.5], [5.8, 3.1, 5.0, 1.7]], dtype=float)
 y = list(classifier.predict(new_samples, as_iterable=True))
 print('Predictions: {}'.format(str(y)))

结果：

Accuracy：0.966667

二.在tf.contrib.learn中创建input函数（输入预处理函数）

格式：

def my_input_fn():

　　# Preprocess your data here...

　　# ...then return 1) a mapping of feature columns to Tensors with
　　# the corresponding feature data, and 2) a Tensor containing labels
　　return feature_cols, labels

完整代码:

 #  Copyright 2016 The TensorFlow Authors. All Rights Reserved.
 #
 #  Licensed under the Apache License, Version 2.0 (the "License");
 #  you may not use this file except in compliance with the License.
 #  You may obtain a copy of the License at
 #
 #   http://www.apache.org/licenses/LICENSE-2.0
 #
 #  Unless required by applicable law or agreed to in writing, software
 #  distributed under the License is distributed on an "AS IS" BASIS,
 #  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 """DNNRegressor with custom input_fn for Housing dataset."""

 from __future__ import absolute_import
 from __future__ import division
 from __future__ import print_function

 import itertools

 import pandas as pd
 import tensorflow as tf

 tf.logging.set_verbosity(tf.logging.INFO)

 COLUMNS = ["crim", "zn", "indus", "nox", "rm", "age",
            "dis", "tax", "ptratio", "medv"]
 FEATURES = ["crim", "zn", "indus", "nox", "rm",
             "age", "dis", "tax", "ptratio"]
 LABEL = "medv"

 def input_fn(data_set):
   feature_cols = {k: tf.constant(data_set[k].values) for k in FEATURES}
   labels = tf.constant(data_set[LABEL].values)
   return feature_cols, labels

 def main(unused_argv):
   # Load datasets
   training_set = pd.read_csv("boston_train.csv", skipinitialspace=True,
                              skiprows=1, names=COLUMNS)
   test_set = pd.read_csv("boston_test.csv", skipinitialspace=True,
                          skiprows=1, names=COLUMNS)

   # Set of 6 examples for which to predict median house values
   prediction_set = pd.read_csv("boston_predict.csv", skipinitialspace=True,
                                skiprows=1, names=COLUMNS)

   # Feature cols
   feature_cols = [tf.contrib.layers.real_valued_column(k)
                   for k in FEATURES]

   # Build 2 layer fully connected DNN with 10, 10 units respectively.
   regressor = tf.contrib.learn.DNNRegressor(feature_columns=feature_cols,
                                             hidden_units=[10, 10],
                                             model_dir="/tmp/boston_model")

   # Fit
   regressor.fit(input_fn=lambda: input_fn(training_set), steps=5000)

   # Score accuracy
   ev = regressor.evaluate(input_fn=lambda: input_fn(test_set), steps=1)
   loss_score = ev["loss"]
   print("Loss: {0:f}".format(loss_score))

   # Print out predictions
   y = regressor.predict(input_fn=lambda: input_fn(prediction_set))
   # .predict() returns an iterator; convert to a list and print predictions
   predictions = list(itertools.islice(y, 6))
   print("Predictions: {}".format(str(predictions)))

 if __name__ == "__main__":
   tf.app.run()

inputfunc_contrib_learn.py

三.TensorFlow可视化(TensorBoard)

代码：

 # Copyright 2015 The TensorFlow Authors. All Rights Reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the 'License');
 # you may not use this file except in compliance with the License.
 # You may obtain a copy of the License at
 #
 #     http://www.apache.org/licenses/LICENSE-2.0
 #
 # Unless required by applicable law or agreed to in writing, software
 # distributed under the License is distributed on an 'AS IS' BASIS,
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
 # ==============================================================================
 """A simple MNIST classifier which displays summaries in TensorBoard.
  This is an unimpressive MNIST model, but it is a good example of using
 tf.name_scope to make a graph legible in the TensorBoard graph explorer, and of
 naming summary tags so that they are grouped meaningfully in TensorBoard.
 It demonstrates the functionality of every TensorBoard dashboard.
 """
 from __future__ import absolute_import
 from __future__ import division
 from __future__ import print_function

 import argparse
 import sys

 import tensorflow as tf

 from tensorflow.examples.tutorials.mnist import input_data

 FLAGS = None

 def train():
   # Import data
   mnist = input_data.read_data_sets(FLAGS.data_dir,
                                     one_hot=True,
                                     fake_data=FLAGS.fake_data)

   sess = tf.InteractiveSession()
   # Create a multilayer model.

   # Input placeholders
   with tf.name_scope('input'):
     x = tf.placeholder(tf.float32, [None, 784], name='x-input')
     y_ = tf.placeholder(tf.float32, [None, 10], name='y-input')

   with tf.name_scope('input_reshape'):
     image_shaped_input = tf.reshape(x, [-1, 28, 28, 1])
     tf.summary.image('input', image_shaped_input, 10)

   # We can't initialize these variables to 0 - the network will get stuck.
   def weight_variable(shape):
     """Create a weight variable with appropriate initialization."""
     initial = tf.truncated_normal(shape, stddev=0.1)
     return tf.Variable(initial)

   def bias_variable(shape):
     """Create a bias variable with appropriate initialization."""
     initial = tf.constant(0.1, shape=shape)
     return tf.Variable(initial)

   def variable_summaries(var):
     """Attach a lot of summaries to a Tensor (for TensorBoard visualization)."""
     with tf.name_scope('summaries'):
       mean = tf.reduce_mean(var)
       tf.summary.scalar('mean', mean)
       with tf.name_scope('stddev'):
         stddev = tf.sqrt(tf.reduce_mean(tf.square(var - mean)))
       tf.summary.scalar('stddev', stddev)
       tf.summary.scalar('max', tf.reduce_max(var))
       tf.summary.scalar('min', tf.reduce_min(var))
       tf.summary.histogram('histogram', var)

   def nn_layer(input_tensor, input_dim, output_dim, layer_name, act=tf.nn.relu):
     """Reusable code for making a simple neural net layer.
     It does a matrix multiply, bias add, and then uses relu to nonlinearize.
     It also sets up name scoping so that the resultant graph is easy to read,
     and adds a number of summary ops.
     """
     # Adding a name scope ensures logical grouping of the layers in the graph.
     with tf.name_scope(layer_name):
       # This Variable will hold the state of the weights for the layer
       with tf.name_scope('weights'):
         weights = weight_variable([input_dim, output_dim])
         variable_summaries(weights)
       with tf.name_scope('biases'):
         biases = bias_variable([output_dim])
         variable_summaries(biases)
       with tf.name_scope('Wx_plus_b'):
         preactivate = tf.matmul(input_tensor, weights) + biases
         tf.summary.histogram('pre_activations', preactivate)
       activations = act(preactivate, name='activation')
       tf.summary.histogram('activations', activations)
       return activations

   hidden1 = nn_layer(x, 784, 500, 'layer1')

   with tf.name_scope('dropout'):
     keep_prob = tf.placeholder(tf.float32)
     tf.summary.scalar('dropout_keep_probability', keep_prob)
     dropped = tf.nn.dropout(hidden1, keep_prob)

   # Do not apply softmax activation yet, see below.
   y = nn_layer(dropped, 500, 10, 'layer2', act=tf.identity)

   with tf.name_scope('cross_entropy'):
     # The raw formulation of cross-entropy,
     #
     # tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(tf.softmax(y)),
     #                               reduction_indices=[1]))
     #
     # can be numerically unstable.
     #
     # So here we use tf.nn.softmax_cross_entropy_with_logits on the
     # raw outputs of the nn_layer above, and then average across
     # the batch.
     diff = tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y)
     with tf.name_scope('total'):
       cross_entropy = tf.reduce_mean(diff)
   tf.summary.scalar('cross_entropy', cross_entropy)

   with tf.name_scope('train'):
     train_step = tf.train.AdamOptimizer(FLAGS.learning_rate).minimize(
         cross_entropy)

   with tf.name_scope('accuracy'):
     with tf.name_scope('correct_prediction'):
       correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
     with tf.name_scope('accuracy'):
       accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
   tf.summary.scalar('accuracy', accuracy)

   # Merge all the summaries and write them out to /tmp/tensorflow/mnist/logs/mnist_with_summaries (by default)
   merged = tf.summary.merge_all()
   train_writer = tf.summary.FileWriter(FLAGS.log_dir + '/train', sess.graph)
   test_writer = tf.summary.FileWriter(FLAGS.log_dir + '/test')
   tf.global_variables_initializer().run()

   # Train the model, and also write summaries.
   # Every 10th step, measure test-set accuracy, and write test summaries
   # All other steps, run train_step on training data, & add training summaries

   def feed_dict(train):
     """Make a TensorFlow feed_dict: maps data onto Tensor placeholders."""
     if train or FLAGS.fake_data:
       xs, ys = mnist.train.next_batch(100, fake_data=FLAGS.fake_data)
       k = FLAGS.dropout
     else:
       xs, ys = mnist.test.images, mnist.test.labels
       k = 1.0
     return {x: xs, y_: ys, keep_prob: k}

   for i in range(FLAGS.max_steps):
     if i % 10 == 0:  # Record summaries and test-set accuracy
       summary, acc = sess.run([merged, accuracy], feed_dict=feed_dict(False))
       test_writer.add_summary(summary, i)
       print('Accuracy at step %s: %s' % (i, acc))
     else:  # Record train set summaries, and train
       if i % 100 == 99:  # Record execution stats
         run_options = tf.RunOptions(trace_level=tf.RunOptions.FULL_TRACE)
         run_metadata = tf.RunMetadata()
         summary, _ = sess.run([merged, train_step],
                               feed_dict=feed_dict(True),
                               options=run_options,
                               run_metadata=run_metadata)
         train_writer.add_run_metadata(run_metadata, 'step%03d' % i)
         train_writer.add_summary(summary, i)
         print('Adding run metadata for', i)
       else:  # Record a summary
         summary, _ = sess.run([merged, train_step], feed_dict=feed_dict(True))
         train_writer.add_summary(summary, i)
   train_writer.close()
   test_writer.close()

 def main(_):
   if tf.gfile.Exists(FLAGS.log_dir):
     tf.gfile.DeleteRecursively(FLAGS.log_dir)
   tf.gfile.MakeDirs(FLAGS.log_dir)
   train()

 if __name__ == '__main__':
   parser = argparse.ArgumentParser()
   parser.add_argument('--fake_data', nargs='?', const=True, type=bool,
                       default=False,
                       help='If true, uses fake data for unit testing.')
   parser.add_argument('--max_steps', type=int, default=1000,
                       help='Number of steps to run trainer.')
   parser.add_argument('--learning_rate', type=float, default=0.001,
                       help='Initial learning rate')
   parser.add_argument('--dropout', type=float, default=0.9,
                       help='Keep probability for training dropout.')
   parser.add_argument('--data_dir', type=str, default='/tmp/tensorflow/mnist/input_data',
                       help='Directory for storing input data')
   parser.add_argument('--log_dir', type=str, default='/tmp/tensorflow/mnist/logs/mnist_with_summaries',
                       help='Summaries log directory')
   FLAGS, unparsed = parser.parse_known_args()
   tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)

mnist_with_summary.py

启动TensorBoard: tensorboard --logdir=path/to/log-directory

小结：

1.重点为高层API tf.contrib.learn的使用；

2.初步了解使用tensorboard的方法；

3.网址：google/tensorflow游乐场

参考文献：谷歌官方文档