[deeplearing-011] tensorflow从入门到精通

1. 官网
    https://www.tensorflow.org/

2. 安装
    2.1 参考文档 https://www.tensorflow.org/install/install_linux
    2.2 在ubuntu上安装cpu支持的tensorflow
        pyenv global anaconda3-5.0.1
        pip install tensorflow
    2.3 验证安装，在python执行如下脚本，如果输出字符串且没有报错，表明安装成功。
------
#Python
import tensorflow as tf
hello = tf.constant('Hello, TensorFlow!')
sess = tf.Session()
print(sess.run(hello))
------

3.tensorflow使用入门
    3.1 文档 https://www.tensorflow.org/get_started/premade_estimators
    3.2  Eager Execution 使用入门。
        入门是一个iris花的分配判别问题。源代码在这里。源代码需要详细的注释。
-------------
from __future__ import absolute_import, division, print_function

import os
import matplotlib.pyplot as plt

import tensorflow as tf
import tensorflow.contrib.eager as tfe

#配置导入和 Eager Execution
tf.enable_eager_execution()
print("TensorFlow version: {}".format(tf.VERSION))
print("Eager execution: {}".format(tf.executing_eagerly()))

#导入和解析训练数据集，数据存放在  /home/brian/.keras/datasets/iris_training.csv
train_dataset_url = "http://download.tensorflow.org/data/iris_training.csv"
train_dataset_fp = tf.keras.utils.get_file(fname=os.path.basename(train_dataset_url),
                                           origin=train_dataset_url)
print("Local copy of the dataset file: {}".format(train_dataset_fp))

#解析数据函数
def parse_csv(line):
  example_defaults = [[0.], [0.], [0.], [0.], [0]]  # sets field types
  parsed_line = tf.decode_csv(line, example_defaults)
  # First 4 fields are features, combine into single tensor
  features = tf.reshape(parsed_line[:-1], shape=(4,))
  # Last field is the label
  label = tf.reshape(parsed_line[-1], shape=())
  return features, label

#解析数据
train_dataset = tf.data.TextLineDataset(train_dataset_fp)
train_dataset = train_dataset.skip(1)             # skip the first header row
train_dataset = train_dataset.map(parse_csv)      # parse each row
train_dataset = train_dataset.shuffle(buffer_size=1000)  # randomize
train_dataset = train_dataset.batch(32)

# View a single example entry from a batch
features, label = iter(train_dataset).next()
print("example features:", features[0])
print("example label:", label[0])

#创建神经网络模型
model = tf.keras.Sequential([
  tf.keras.layers.Dense(10, activation="relu", input_shape=(4,)),  # input shape required
  tf.keras.layers.Dense(10, activation="relu"),
  tf.keras.layers.Dense(3)
])

#训练：定义损失函数
def loss(model, x, y):
  y_ = model(x)
  return tf.losses.sparse_softmax_cross_entropy(labels=y, logits=y_)

def grad(model, inputs, targets):
  with tf.GradientTape() as tape:
    loss_value = loss(model, inputs, targets)
  return tape.gradient(loss_value, model.variables)

#创建优化器
optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.01)

#开始训练
# keep results for plotting
train_loss_results = []
train_accuracy_results = []

num_epochs = 201

for epoch in range(num_epochs):
  epoch_loss_avg = tfe.metrics.Mean()
  epoch_accuracy = tfe.metrics.Accuracy()

  # Training loop - using batches of 32
  for x, y in train_dataset:
    # Optimize the model
    grads = grad(model, x, y)
    optimizer.apply_gradients(zip(grads, model.variables),
                              global_step=tf.train.get_or_create_global_step())

    # Track progress
    epoch_loss_avg(loss(model, x, y))  # add current batch loss
    # compare predicted label to actual label
    epoch_accuracy(tf.argmax(model(x), axis=1, output_type=tf.int32), y)

  # end epoch
  train_loss_results.append(epoch_loss_avg.result())
  train_accuracy_results.append(epoch_accuracy.result())

  if epoch % 50 == 0:
    print("Epoch {:03d}: Loss: {:.3f}, Accuracy: {:.3%}".format(epoch,
                                                                epoch_loss_avg.result(),
                                                                epoch_accuracy.result()))

#绘制结果
fig, axes = plt.subplots(2, sharex=True, figsize=(12, 8))
fig.suptitle('Training Metrics')

axes[0].set_ylabel("Loss", fontsize=14)
axes[0].plot(train_loss_results)

axes[1].set_ylabel("Accuracy", fontsize=14)
axes[1].set_xlabel("Epoch", fontsize=14)
axes[1].plot(train_accuracy_results)

plt.show()

#设置测试数据集
test_url = "http://download.tensorflow.org/data/iris_test.csv"

test_fp = tf.keras.utils.get_file(fname=os.path.basename(test_url),
                                  origin=test_url)

test_dataset = tf.data.TextLineDataset(test_fp)
test_dataset = test_dataset.skip(1)             # skip header row
test_dataset = test_dataset.map(parse_csv)      # parse each row with the funcition created earlier
test_dataset = test_dataset.shuffle(1000)       # randomize
test_dataset = test_dataset.batch(32)           # use the same batch size as the training set

#
test_accuracy = tfe.metrics.Accuracy()

for (x, y) in test_dataset:
  prediction = tf.argmax(model(x), axis=1, output_type=tf.int32)
  test_accuracy(prediction, y)

print("Test set accuracy: {:.3%}".format(test_accuracy.result()))

#进行预测
class_ids = ["Iris setosa", "Iris versicolor", "Iris virginica"]

predict_dataset = tf.convert_to_tensor([
    [5.1, 3.3, 1.7, 0.5,],
    [5.9, 3.0, 4.2, 1.5,],
    [6.9, 3.1, 5.4, 2.1]
])

predictions = model(predict_dataset)

for i, logits in enumerate(predictions):
  class_idx = tf.argmax(logits).numpy()
  name = class_ids[class_idx]
  print("Example {} prediction: {}".format(i, name))
-------------