Google TensorFlow课程 编程笔记（10）———使用神经网络对手写数字进行分类

 

使用神经网络对手写数字进行分类

学习目标：

• 训练线性模型和神经网络，以对传统 MNIST 数据集中的手写数字进行分类
• 比较线性分类模型和神经网络分类模型的效果
• 可视化神经网络隐藏层的权重

---

我们的目标是将每个输入图片与正确的数字相对应。我们会创建一个包含几个隐藏层的神经网络，并在顶部放置一个归一化指数层，以选出最合适的类别。

第1步：设置：加载必要的库+加载数据+数据预处理

from __future__ import print_function

import glob
import math
import os

from IPython import display
from matplotlib import cm
from matplotlib import gridspec
from matplotlib import pyplot as plt
import numpy as np
import pandas as pd
import seaborn as sns
from sklearn import metrics
import tensorflow as tf
from tensorflow.python.data import Dataset

tf.logging.set_verbosity(tf.logging.ERROR)
pd.options.display.max_rows = 10
pd.options.display.float_format = '{:.1f}'.format

mnist_dataframe = pd.read_csv(
  "https://download.mlcc.google.com/mledu-datasets/mnist_train_small.csv",
  sep=",",
  header=None)

# Use just the first 10,000 records for training/validation
mnist_dataframe = mnist_dataframe.head(10000)

mnist_dataframe = mnist_dataframe.reindex(np.random.permutation(mnist_dataframe.index))
mnist_dataframe.head()

第一列中包含类别标签。其余列中包含特征值，每个像素对应一个特征值，有 28×28=784 个像素值，其中大部分像素值都为零；您也许需要花一分钟时间来确认它们不全部为零。

这些样本都是分辨率相对较低、对比度相对较高的手写数字图片。0-9 这十个数字中的每个可能出现的数字均由唯一的类别标签表示。因此，这是一个具有 10 个类别的多类别分类问题。

现在，我们解析一下标签和特征，并查看几个样本。注意 loc 的使用，借助 loc，我们能够基于原来的位置抽出各列，因为此数据集中没有标题行。

def parse_labels_and_features(dataset):
  """Extracts labels and features.
  
  This is a good place to scale or transform the features if needed.
  
  Args:
    dataset: A Pandas `Dataframe`, containing the label on the first column and
      monochrome pixel values on the remaining columns, in row major order.
  Returns:
    A `tuple` `(labels, features)`:
      labels: A Pandas `Series`.
      features: A Pandas `DataFrame`.
  """
  labels = dataset[0]    #数据的第0列为标签列

  # DataFrame.loc index ranges are inclusive at both ends.
  features = dataset.loc[:,1:784]    #数据第1~784行为数据内容列
  # Scale the data to [0, 1] by dividing out the max value, 255.
  features = features / 255      #通过除以255把特征值缩小到[0，1]之间

  return labels, features

预览数据集：

training_targets, training_examples = parse_labels_and_features(mnist_dataframe[:7500])
training_examples.describe()

第2步：样本特征列的选择

rand_example = np.random.choice(training_examples.index)
_, ax = plt.subplots()
ax.matshow(training_examples.loc[rand_example].values.reshape(28, 28))
ax.set_title("Label: %i" % training_targets.loc[rand_example])
ax.grid(False)

第三步：样本特征列的选择

def construct_feature_columns():
  """Construct the TensorFlow Feature Columns.

  Returns:
    A set of feature columns
  """ 
  
  # There are 784 pixels in each image 
  return set([tf.feature_column.numeric_column('pixels', shape=784)])

*对比示范第3步*：为 MNIST 构建线性模型

在本次练习中，我们会对训练和预测使用单独的输入函数，并将这些函数分别嵌套在 create_training_input_fn() 和 create_predict_input_fn() 中，这样一来，我们就可以调用这些函数，以返回相应的 _input_fn，并将其传递到 .train() 和 .predict() 调用。

def create_training_input_fn(features, labels, batch_size, num_epochs=None, shuffle=True):
  """A custom input_fn for sending MNIST data to the estimator for training.

  Args:
    features: The training features.
    labels: The training labels.
    batch_size: Batch size to use during training.

  Returns:
    A function that returns batches of training features and labels during
    training.
  """
  def _input_fn(num_epochs=None, shuffle=True):
    # Input pipelines are reset with each call to .train(). To ensure model
    # gets a good sampling of data, even when steps is small, we 
    # shuffle all the data before creating the Dataset object
    idx = np.random.permutation(features.index)
    raw_features = {"pixels":features.reindex(idx)}#打乱顺序并重新索引
    raw_targets = np.array(labels[idx])
   
    ds = Dataset.from_tensor_slices((raw_features,raw_targets)) # warning: 2GB limit
    ds = ds.batch(batch_size).repeat(num_epochs)
    
    if shuffle:
      ds = ds.shuffle(10000)
    
    # Return the next batch of data
    feature_batch, label_batch = ds.make_one_shot_iterator().get_next()
    return feature_batch, label_batch

  return _input_fn

def create_predict_input_fn(features, labels, batch_size):
  """A custom input_fn for sending mnist data to the estimator for predictions.

  Args:
    features: The features to base predictions on.
    labels: The labels of the prediction examples.

  Returns:
    A function that returns features and labels for predictions.
  """
  def _input_fn():
    raw_features = {"pixels": features.values}
    raw_targets = np.array(labels)
    
    ds = Dataset.from_tensor_slices((raw_features, raw_targets)) # warning: 2GB limit
    ds = ds.batch(batch_size)
    
        
    # Return the next batch of data
    feature_batch, label_batch = ds.make_one_shot_iterator().get_next()
    return feature_batch, label_batch

  return _input_fn

def train_linear_classification_model(
    learning_rate,
    steps,
    batch_size,
    training_examples,
    training_targets,
    validation_examples,
    validation_targets):
  """Trains a linear classification model for the MNIST digits dataset.
  
  In addition to training, this function also prints training progress information,
  a plot of the training and validation loss over time, and a confusion
  matrix.
  
  Args:
    learning_rate: An `int`, the learning rate to use.
    steps: A non-zero `int`, the total number of training steps. A training step
      consists of a forward and backward pass using a single batch.
    batch_size: A non-zero `int`, the batch size.
    training_examples: A `DataFrame` containing the training features.
    training_targets: A `DataFrame` containing the training labels.
    validation_examples: A `DataFrame` containing the validation features.
    validation_targets: A `DataFrame` containing the validation labels.
      
  Returns:
    The trained `LinearClassifier` object.
  """

  periods = 10

  steps_per_period = steps / periods  
  # Create the input functions.
  predict_training_input_fn = create_predict_input_fn(
    training_examples, training_targets, batch_size)
  predict_validation_input_fn = create_predict_input_fn(
    validation_examples, validation_targets, batch_size)
  training_input_fn = create_training_input_fn(
    training_examples, training_targets, batch_size)
  
  # Create a LinearClassifier object.
  my_optimizer = tf.train.AdagradOptimizer(learning_rate=learning_rate)
  my_optimizer = tf.contrib.estimator.clip_gradients_by_norm(my_optimizer, 5.0)
  classifier = tf.estimator.LinearClassifier(
      feature_columns=construct_feature_columns(),
      n_classes=10,
      optimizer=my_optimizer,
      config=tf.estimator.RunConfig(keep_checkpoint_max=1)
  )

  # Train the model, but do so inside a loop so that we can periodically assess
  # loss metrics.
  print("Training model...")
  print("LogLoss error (on validation data):")
  training_errors = []
  validation_errors = []
  for period in range (0, periods):
    # Train the model, starting from the prior state.
    classifier.train(
        input_fn=training_input_fn,
        steps=steps_per_period
    )
  
    # Take a break and compute probabilities.
    training_predictions = list(classifier.predict(input_fn=predict_training_input_fn))
    training_probabilities = np.array([item['probabilities'] for item in training_predictions])
    training_pred_class_id = np.array([item['class_ids'][0] for item in training_predictions])
    training_pred_one_hot = tf.keras.utils.to_categorical(training_pred_class_id,10)
        
    validation_predictions = list(classifier.predict(input_fn=predict_validation_input_fn))
    validation_probabilities = np.array([item['probabilities'] for item in validation_predictions])    
    validation_pred_class_id = np.array([item['class_ids'][0] for item in validation_predictions])
    validation_pred_one_hot = tf.keras.utils.to_categorical(validation_pred_class_id,10)    
    
    # Compute training and validation errors.
    training_log_loss = metrics.log_loss(training_targets, training_pred_one_hot)
    validation_log_loss = metrics.log_loss(validation_targets, validation_pred_one_hot)
    # Occasionally print the current loss.
    print("  period %02d : %0.2f" % (period, validation_log_loss))
    # Add the loss metrics from this period to our list.
    training_errors.append(training_log_loss)
    validation_errors.append(validation_log_loss)
  print("Model training finished.")
  # Remove event files to save disk space.
  _ = map(os.remove, glob.glob(os.path.join(classifier.model_dir, 'events.out.tfevents*')))
  
  # Calculate final predictions (not probabilities, as above).
  final_predictions = classifier.predict(input_fn=predict_validation_input_fn)
  final_predictions = np.array([item['class_ids'][0] for item in final_predictions])
  
  
  accuracy = metrics.accuracy_score(validation_targets, final_predictions)
  print("Final accuracy (on validation data): %0.2f" % accuracy)

  # Output a graph of loss metrics over periods.
  plt.ylabel("LogLoss")
  plt.xlabel("Periods")
  plt.title("LogLoss vs. Periods")
  plt.plot(training_errors, label="training")
  plt.plot(validation_errors, label="validation")
  plt.legend()
  plt.show()
  
  # Output a plot of the confusion matrix.
  cm = metrics.confusion_matrix(validation_targets, final_predictions)
  # Normalize the confusion matrix by row (i.e by the number of samples
  # in each class)
  cm_normalized = cm.astype("float") / cm.sum(axis=1)[:, np.newaxis]
  ax = sns.heatmap(cm_normalized, cmap="bone_r")
  ax.set_aspect(1)
  plt.title("Confusion matrix")
  plt.ylabel("True label")
  plt.xlabel("Predicted label")
  plt.show()

  return classifier

*对比示范第4步*：调整训练模型参数开始训练

_ = train_linear_classification_model(
    learning_rate=0.03,
    steps=1000,
    batch_size=30,
    training_examples=training_examples,
    training_targets=training_targets,
    validation_examples=validation_examples,
    validation_targets=validation_targets)

该线性模型经过多次调试，最后获得了一个比较高的准确率90%

使用神经网络替换线性分类器

第3步：创建神经网络模型

def train_nn_classification_model(
    learning_rate,
    steps,
    batch_size,
    hidden_units,         #配置隐藏单元
    training_examples,
    training_targets,
    validation_examples,
    validation_targets):
  """Trains a neural network classification model for the MNIST digits dataset.
  
  In addition to training, this function also prints training progress information,
  a plot of the training and validation loss over time, as well as a confusion
  matrix.
  
  Args:
    learning_rate: An `int`, the learning rate to use.
    steps: A non-zero `int`, the total number of training steps. A training step
      consists of a forward and backward pass using a single batch.
    batch_size: A non-zero `int`, the batch size.
    hidden_units: A `list` of int values, specifying the number of neurons in each layer.#隐藏单元
    training_examples: A `DataFrame` containing the training features.
    training_targets: A `DataFrame` containing the training labels.
    validation_examples: A `DataFrame` containing the validation features.
    validation_targets: A `DataFrame` containing the validation labels.
      
  Returns:
    The trained `DNNClassifier` object.
  """

  periods = 10
  # Caution: input pipelines are reset with each call to train. 
  # If the number of steps is small, your model may never see most of the data.  
  # So with multiple `.train` calls like this you may want to control the length 
  # of training with num_epochs passed to the input_fn. Or, you can do a really-big shuffle, 
  # or since it's in-memory data, shuffle all the data in the `input_fn`.
  steps_per_period = steps / periods  
  # Create the input functions.
  predict_training_input_fn = create_predict_input_fn(
    training_examples, training_targets, batch_size)
  predict_validation_input_fn = create_predict_input_fn(
    validation_examples, validation_targets, batch_size)
  training_input_fn = create_training_input_fn(
    training_examples, training_targets, batch_size)
  
  # Create the input functions.
  predict_training_input_fn = create_predict_input_fn(
    training_examples, training_targets, batch_size)
  predict_validation_input_fn = create_predict_input_fn(
    validation_examples, validation_targets, batch_size)
  training_input_fn = create_training_input_fn(
    training_examples, training_targets, batch_size)
  
  # Create feature columns.
  feature_columns = [tf.feature_column.numeric_column('pixels', shape=784)]

  # Create a DNNClassifier object.
  my_optimizer = tf.train.AdagradOptimizer(learning_rate=learning_rate)
  my_optimizer = tf.contrib.estimator.clip_gradients_by_norm(my_optimizer, 5.0)
  classifier = tf.estimator.DNNClassifier(                   #DNNClassifier 
      feature_columns=feature_columns,
      n_classes=10,
      hidden_units=hidden_units,#隐藏单元
      optimizer=my_optimizer,
      config=tf.contrib.learn.RunConfig(keep_checkpoint_max=1)#隐藏单元配置
  )

  # Train the model, but do so inside a loop so that we can periodically assess
  # loss metrics.
  print("Training model...")
  print("LogLoss error (on validation data):")
  training_errors = []
  validation_errors = []
  for period in range (0, periods):
    # Train the model, starting from the prior state.
    classifier.train(
        input_fn=training_input_fn,
        steps=steps_per_period
    )
  
    # Take a break and compute probabilities.
    training_predictions = list(classifier.predict(input_fn=predict_training_input_fn))
    training_probabilities = np.array([item['probabilities'] for item in training_predictions])
    training_pred_class_id = np.array([item['class_ids'][0] for item in training_predictions])
    training_pred_one_hot = tf.keras.utils.to_categorical(training_pred_class_id,10)
        
    validation_predictions = list(classifier.predict(input_fn=predict_validation_input_fn))
    validation_probabilities = np.array([item['probabilities'] for item in validation_predictions])    
    validation_pred_class_id = np.array([item['class_ids'][0] for item in validation_predictions])
    validation_pred_one_hot = tf.keras.utils.to_categorical(validation_pred_class_id,10)    
    
    # Compute training and validation errors.
    training_log_loss = metrics.log_loss(training_targets, training_pred_one_hot)
    validation_log_loss = metrics.log_loss(validation_targets, validation_pred_one_hot)
    # Occasionally print the current loss.
    print("  period %02d : %0.2f" % (period, validation_log_loss))
    # Add the loss metrics from this period to our list.
    training_errors.append(training_log_loss)
    validation_errors.append(validation_log_loss)
  print("Model training finished.")
  # Remove event files to save disk space.
  _ = map(os.remove, glob.glob(os.path.join(classifier.model_dir, 'events.out.tfevents*')))
  
  # Calculate final predictions (not probabilities, as above).
  final_predictions = classifier.predict(input_fn=predict_validation_input_fn)
  final_predictions = np.array([item['class_ids'][0] for item in final_predictions])
  
  
  accuracy = metrics.accuracy_score(validation_targets, final_predictions)
  print("Final accuracy (on validation data): %0.2f" % accuracy)

  # Output a graph of loss metrics over periods.
  plt.ylabel("LogLoss")
  plt.xlabel("Periods")
  plt.title("LogLoss vs. Periods")
  plt.plot(training_errors, label="training")
  plt.plot(validation_errors, label="validation")
  plt.legend()
  plt.show()
  
  # Output a plot of the confusion matrix.
  cm = metrics.confusion_matrix(validation_targets, final_predictions)
  # Normalize the confusion matrix by row (i.e by the number of samples
  # in each class)
  cm_normalized = cm.astype("float") / cm.sum(axis=1)[:, np.newaxis]
  ax = sns.heatmap(cm_normalized, cmap="bone_r")
  ax.set_aspect(1)
  plt.title("Confusion matrix")
  plt.ylabel("True label")
  plt.xlabel("Predicted label")
  plt.show()

  return classifier

第4步：调整训练模型参数开始训练

classifier = train_nn_classification_model(
    learning_rate=0.05,
    steps=1000,
    batch_size=30,
    hidden_units=[100, 100],
    training_examples=training_examples,
    training_targets=training_targets,
    validation_examples=validation_examples,
    validation_targets=validation_targets)

第5步：验证测试集的准确率

mnist_test_dataframe = pd.read_csv(
  "https://download.mlcc.google.com/mledu-datasets/mnist_test.csv",
  sep=",",
  header=None)

test_targets, test_examples = parse_labels_and_features(mnist_test_dataframe)
test_examples.describe()

predict_test_input_fn = create_predict_input_fn(
    test_examples, test_targets, batch_size=100)

test_predictions = classifier.predict(input_fn=predict_test_input_fn)
test_predictions = np.array([item['class_ids'][0] for item in test_predictions])
  
accuracy = metrics.accuracy_score(test_targets, test_predictions)
print("Accuracy on test data: %0.2f" % accuracy)

使用深度神经网络之后，准确率达到了94%。效果有明显提升。

额外任务 3：可视化第一个隐藏层的权重

我们来花几分钟时间看看模型的 weights_ 属性，以深入探索我们的神经网络，并了解它学到了哪些规律。

模型的输入层有 784 个权重，对应于 28×28 像素输入图片。第一个隐藏层将有 784×N 个权重，其中 N 指的是该层中的节点数。我们可以将这些权重重新变回 28×28像素的图片，具体方法是将 N 个 1×784 权重数组变形为 N 个 28×28 大小数组。

运行以下单元格，绘制权重曲线图。请注意，此单元格要求名为 "classifier" 的 DNNClassifier 已经过训练。

print(classifier.get_variable_names())

weights0 = classifier.get_variable_value("dnn/hiddenlayer_0/kernel")

print("weights0 shape:", weights0.shape)

num_nodes = weights0.shape[1]
num_rows = int(math.ceil(num_nodes / 10.0))
fig, axes = plt.subplots(num_rows, 10, figsize=(20, 2 * num_rows))
for coef, ax in zip(weights0.T, axes.ravel()):
    # Weights in coef is reshaped from 1x784 to 28x28.
    ax.matshow(coef.reshape(28, 28), cmap=plt.cm.pink)
    ax.set_xticks(())
    ax.set_yticks(())

plt.show()

神经网络的第一个隐藏层应该会对一些级别特别低的特征进行建模，因此可视化权重可能只显示一些模糊的区域，也可能只显示数字的某几个部分。此外，您可能还会看到一些基本上是噪点（这些噪点要么不收敛，要么被更高的层忽略）的神经元。

好吧，反正我是看得一脸懵逼！只能看出图中的凹凸部分很像是写字时候的部分轨迹。还有部分很像二维码的应该是噪点吧。

 

 

本文仅为个人学习笔记记录，请结合Google 机器学习，编程练习：使用神经网络对手写数字进行分类，进行阅读

编程练习地址：https://colab.research.google.com/notebooks/mlcc/multi-class_classification_of_handwritten_digits.ipynb?hl=zh-cn#scrollTo=ZfzsTYGPPU8I