[譯] TensorFlow 教程 #03 - PrettyTensor

時間 2019-11-29

標籤 tensorflow 教程 prettytensor 简体版

原文原文鏈接

題圖來自: githubpython

本文主要介紹了PrettyTensor，用來快速構建神經網絡。
固然，原文寫於16年，如今有更方便的API，後續會介紹。
本文有大段前篇教程的文字及代碼，若是看過上一篇的朋友能夠快速翻到下文PrettyTensor實現的那一部分去。git

01 - 簡單線性模型 / 02 - 卷積神經網絡github

by Magnus Erik Hvass Pedersen / GitHub / Videos on YouTube
中文翻譯 thrillerist / Githubwindows

若有轉載，請附上本文連接。api

介紹

以前的教程演示瞭如何在TensorFlow中實現一個卷積神經網絡，這須要瞭解一些TensorFlow工做的底層原理。它有點複雜，實現起來還容易犯錯。bash

這篇教程爲咱們說明了如何使用TensorFlow的一個附加包PrettyTensor，它也是Google開發的。PrettyTensor提供了在TensorFlow中建立神經網絡的更簡單的方法，讓咱們能夠關注本身想要實現的想法，而不用過多擔憂底層的實現細節。這也讓代碼更短、更容易閱讀和修改。網絡

除了用PrettyTensor構造圖以外，這篇教程的大部分代碼和教程 #02 中的同樣，固然還有一些細微的變化。session

這篇教程是基於教程 #02 之上的，若是你是TensorFlow新手的話，推薦先學完上一份教程。你須要熟悉基本的線性代數、Python和Jupyter Notebook編輯器。編輯器

流程圖

下面的圖表直接展現了以後實現的卷積神經網絡中數據的傳遞。關於卷積的詳細描述請看上一篇教程。ide

from IPython.display import Image
Image('images/02_network_flowchart.png')複製代碼

輸入圖像在第一層卷基層中用權重過濾器處理。結果在16張新圖裏，每一個表明了卷積層裏一個過濾器（的處理結果）。圖像也通過降採樣，所以圖像分辨率從28x28減小到14x14。

這16張小圖在第二個卷積層中處理。這16個通道都須要一個權重過濾，這層的輸出的每一個通道也各須要一個權重過濾。總共有36個輸出，因此在第二個卷積層有16 x 36 = 576個濾波器。輸出圖再一次降採樣到7x7個像素。

第二個卷積層的輸出是36張7x7像素的圖像。它們被壓到一個長爲7 x 7 x 36 = 1764的向量中去，它做爲一個有128個神經元（或元素）的全鏈接網絡的輸入。這些又輸入到另外一個有10個神經元的全鏈接層中，每一個神經元表明一個類別，用來肯定圖像的類別，也即圖像上的數字。

卷積濾波一開始是隨機挑選的，所以分類也是隨機完成的。根據交叉熵（cross-entropy）來測量輸入圖預測值和真實類別間的錯誤。而後優化器用鏈式法則自動地將這個偏差傳在卷積網絡中傳遞，更新濾波權重來提高分類質量。這個過程迭代了幾千次，直到分類偏差足夠低。

這些特定的濾波權重和中間圖像是一個優化的結果，和你執行這些代碼所看到的可能會有所不一樣。

注意，這些在TensorFlow上的計算是在一部分圖像上執行，而非單獨的一張圖，這使得計算更有效。也意味着在TensorFlow上實現時，這個流程圖實際上會有更多的數據維度。

導入

%matplotlib inline
import matplotlib.pyplot as plt
import tensorflow as tf
import numpy as np
from sklearn.metrics import confusion_matrix
import time
from datetime import timedelta
import math

# We also need PrettyTensor.
import prettytensor as pt複製代碼

使用Python3.5.2（Anaconda）開發，TensorFlow版本是：

tf.__version__複製代碼

'0.12.0-rc0'

PrettyTensor 版本:

pt.__version__複製代碼

'0.7.1'

載入數據

MNIST數據集大約12MB，若是沒在給定路徑中找到就會自動下載。

from tensorflow.examples.tutorials.mnist import input_data
data = input_data.read_data_sets('data/MNIST/', one_hot=True)複製代碼

Extracting data/MNIST/train-images-idx3-ubyte.gz
Extracting data/MNIST/train-labels-idx1-ubyte.gz
Extracting data/MNIST/t10k-images-idx3-ubyte.gz
Extracting data/MNIST/t10k-labels-idx1-ubyte.gz

如今已經載入了MNIST數據集，它由70,000張圖像和對應的標籤（好比圖像的類別）組成。數據集分紅三份互相獨立的子集。咱們在教程中只用訓練集和測試集。

print("Size of:")
print("- Training-set:\t\t{}".format(len(data.train.labels)))
print("- Test-set:\t\t{}".format(len(data.test.labels)))
print("- Validation-set:\t{}".format(len(data.validation.labels)))複製代碼

Size of:
-Training-set: 55000
-Test-set: 10000
-Validation-set: 5000

類型標籤使用One-Hot編碼，這意外每一個標籤是長爲10的向量，除了一個元素以外，其餘的都爲零。這個元素的索引就是類別的數字，即相應圖片中畫的數字。咱們也須要測試數據集類別數字的整型值，用下面的方法來計算。

data.test.cls = np.argmax(data.test.labels, axis=1)複製代碼

數據維度

在下面的源碼中，有不少地方用到了數據維度。它們只在一個地方定義，所以咱們能夠在代碼中使用這些數字而不是直接寫數字。

# We know that MNIST images are 28 pixels in each dimension.
img_size = 28

# Images are stored in one-dimensional arrays of this length.
img_size_flat = img_size * img_size

# Tuple with height and width of images used to reshape arrays.
img_shape = (img_size, img_size)

# Number of colour channels for the images: 1 channel for gray-scale.
num_channels = 1

# Number of classes, one class for each of 10 digits.
num_classes = 10複製代碼

用來繪製圖片的幫助函數

這個函數用來在3x3的柵格中畫9張圖像，而後在每張圖像下面寫出真實類別和預測類別。

def plot_images(images, cls_true, cls_pred=None):
    assert len(images) == len(cls_true) == 9

    # Create figure with 3x3 sub-plots.
    fig, axes = plt.subplots(3, 3)
    fig.subplots_adjust(hspace=0.3, wspace=0.3)

    for i, ax in enumerate(axes.flat):
        # Plot image.
        ax.imshow(images[i].reshape(img_shape), cmap='binary')

        # Show true and predicted classes.
        if cls_pred is None:
            xlabel = "True: {0}".format(cls_true[i])
        else:
            xlabel = "True: {0}, Pred: {1}".format(cls_true[i], cls_pred[i])

        # Show the classes as the label on the x-axis.
        ax.set_xlabel(xlabel)

        # Remove ticks from the plot.
        ax.set_xticks([])
        ax.set_yticks([])

    # Ensure the plot is shown correctly with multiple plots
    # in a single Notebook cell.
    plt.show()複製代碼

繪製幾張圖像來看看數據是否正確

# Get the first images from the test-set.
images = data.test.images[0:9]

# Get the true classes for those images.
cls_true = data.test.cls[0:9]

# Plot the images and labels using our helper-function above.
plot_images(images=images, cls_true=cls_true)複製代碼

TensorFlow圖

TensorFlow的所有目的就是使用一個稱之爲計算圖（computational graph）的東西，它會比直接在Python中進行相同計算量要高效得多。TensorFlow比Numpy更高效，由於TensorFlow瞭解整個須要運行的計算圖，然而Numpy只知道某個時間點上惟一的數學運算。

TensorFlow也可以自動地計算須要優化的變量的梯度，使得模型有更好的表現。這是因爲圖是簡單數學表達式的結合，所以整個圖的梯度能夠用鏈式法則推導出來。

TensorFlow還能利用多核CPU和GPU，Google也爲TensorFlow製造了稱爲TPUs（Tensor Processing Units）的特殊芯片，它比GPU更快。

一個TensorFlow圖由下面幾個部分組成，後面會詳細描述：

佔位符變量（Placeholder）用來改變圖的輸入。
模型變量（Model）將會被優化，使得模型表現得更好。
模型本質上就是一些數學函數，它根據Placeholder和模型的輸入變量來計算一些輸出。
一個cost度量用來指導變量的優化。
一個優化策略會更新模型的變量。

另外，TensorFlow圖也包含了一些調試狀態，好比用TensorBoard打印log數據，本教程不涉及這些。

佔位符（Placeholder）變量

Placeholder是做爲圖的輸入，咱們每次運行圖的時候均可能改變它們。將這個過程稱爲feeding placeholder變量，後面將會描述這個。

首先咱們爲輸入圖像定義placeholder變量。這讓咱們能夠改變輸入到TensorFlow圖中的圖像。這也是一個張量（tensor），表明一個多維向量或矩陣。數據類型設置爲float32，形狀設爲[None, img_size_flat]，None表明tensor可能保存着任意數量的圖像，每張圖象是一個長度爲img_size_flat的向量。

x = tf.placeholder(tf.float32, shape=[None, img_size_flat], name='x')複製代碼

卷積層但願x被編碼爲4維張量，所以咱們須要將它的形狀轉換至[num_images, img_height, img_width, num_channels]。注意img_height == img_width == img_size，若是第一維的大小設爲-1，num_images的大小也會被自動推導出來。轉換運算以下：

x_image = tf.reshape(x, [-1, img_size, img_size, num_channels])複製代碼

接下來咱們爲輸入變量x中的圖像所對應的真實標籤訂義placeholder變量。變量的形狀是[None, num_classes]，這表明着它保存了任意數量的標籤，每一個標籤是長度爲num_classes的向量，本例中長度爲10。

y_true = tf.placeholder(tf.float32, shape=[None, 10], name='y_true')複製代碼

咱們也能夠爲class-number提供一個placeholder，但這裏用argmax來計算它。這裏只是TensorFlow中的一些操做，沒有執行什麼運算。

y_true_cls = tf.argmax(y_true, dimension=1)複製代碼

TensorFlow 實現

這一節顯示了教程 #02 中直接用TensorFlow實現卷積神經網絡的源代碼。這份Notebook中並無直接用到這些代碼，只是爲了方便和下面PrettyTensor的實現進行比較。

這裏要注意的是有多少代碼量以及TensorFlow保存數據、進行運算的底層細節。即便在很小的神經網絡中也容易犯錯。

幫助函數

在直接用TensorFlow實現時，咱們建立一些在構造圖時經常使用到的幫助函數。

這兩個函數在TensorFlow圖中建立新的變量並用隨機值初始化。

def new_weights(shape):
    return tf.Variable(tf.truncated_normal(shape, stddev=0.05))複製代碼

def new_biases(length):
    return tf.Variable(tf.constant(0.05, shape=[length]))複製代碼

下面的幫助函數建立一個新的卷積網絡。輸入和輸出是4維的張量（4-rank tensors）。注意TensorFlow API的底層細節，好比權重變量的大小。這裏很容易犯錯，可能會致使奇怪的錯誤信息，而且很難調試。

def new_conv_layer(input, # The previous layer. num_input_channels, # Num. channels in prev. layer. filter_size, # Width and height of filters. num_filters, # Number of filters. use_pooling=True):  # Use 2x2 max-pooling.

    # Shape of the filter-weights for the convolution.
    # This format is determined by the TensorFlow API.
    shape = [filter_size, filter_size, num_input_channels, num_filters]

    # Create new weights aka. filters with the given shape.
    weights = new_weights(shape=shape)

    # Create new biases, one for each filter.
    biases = new_biases(length=num_filters)

    # Create the TensorFlow operation for convolution.
    # Note the strides are set to 1 in all dimensions.
    # The first and last stride must always be 1,
    # because the first is for the image-number and
    # the last is for the input-channel.
    # But e.g. strides=[1, 2, 2, 1] would mean that the filter
    # is moved 2 pixels across the x- and y-axis of the image.
    # The padding is set to 'SAME' which means the input image
    # is padded with zeroes so the size of the output is the same.
    layer = tf.nn.conv2d(input=input,
                         filter=weights,
                         strides=[1, 1, 1, 1],
                         padding='SAME')

    # Add the biases to the results of the convolution.
    # A bias-value is added to each filter-channel.
    layer += biases

    # Use pooling to down-sample the image resolution?
    if use_pooling:
        # This is 2x2 max-pooling, which means that we
        # consider 2x2 windows and select the largest value
        # in each window. Then we move 2 pixels to the next window.
        layer = tf.nn.max_pool(value=layer,
                               ksize=[1, 2, 2, 1],
                               strides=[1, 2, 2, 1],
                               padding='SAME')

    # Rectified Linear Unit (ReLU).
    # It calculates max(x, 0) for each input pixel x.
    # This adds some non-linearity to the formula and allows us
    # to learn more complicated functions.
    layer = tf.nn.relu(layer)

    # Note that ReLU is normally executed before the pooling,
    # but since relu(max_pool(x)) == max_pool(relu(x)) we can
    # save 75% of the relu-operations by max-pooling first.

    # We return both the resulting layer and the filter-weights
    # because we will plot the weights later.
    return layer, weights複製代碼

下面的幫助函數將一個4維張量轉換到2維，所以咱們能夠在卷積層以後添加一個全鏈接層。

def flatten_layer(layer):
    # Get the shape of the input layer.
    layer_shape = layer.get_shape()

    # The shape of the input layer is assumed to be:
    # layer_shape == [num_images, img_height, img_width, num_channels]

    # The number of features is: img_height * img_width * num_channels
    # We can use a function from TensorFlow to calculate this.
    num_features = layer_shape[1:4].num_elements()

    # Reshape the layer to [num_images, num_features].
    # Note that we just set the size of the second dimension
    # to num_features and the size of the first dimension to -1
    # which means the size in that dimension is calculated
    # so the total size of the tensor is unchanged from the reshaping.
    layer_flat = tf.reshape(layer, [-1, num_features])

    # The shape of the flattened layer is now:
    # [num_images, img_height * img_width * num_channels]

    # Return both the flattened layer and the number of features.
    return layer_flat, num_features複製代碼

接下來的幫助函數建立一個全鏈接層。

def new_fc_layer(input, # The previous layer. num_inputs, # Num. inputs from prev. layer. num_outputs, # Num. outputs. use_relu=True): # Use Rectified Linear Unit (ReLU)?

    # Create new weights and biases.
    weights = new_weights(shape=[num_inputs, num_outputs])
    biases = new_biases(length=num_outputs)

    # Calculate the layer as the matrix multiplication of
    # the input and weights, and then add the bias-values.
    layer = tf.matmul(input, weights) + biases

    # Use ReLU?
    if use_relu:
        layer = tf.nn.relu(layer)

    return layer複製代碼

構造圖（Graph）

如今將會用上面的幫助函數來建立卷積神經網絡。若是沒有這些函數的話，代碼將會又長又難以理解。

注意，咱們並不會運行下面的代碼。寫在這裏只是爲了與PrettyTensor的代碼進行比較。

以前的教程使用定義好的常量，所以很容易改變（變量）。好比，咱們沒有將 filter_size=5 看成 new_conv_layer()的參數，而是令filter_size=filter_size1，而後在其餘地方定義filter_size1=5。這樣子就很容易改變全部的常量。

if False:  # Don't execute this! Just show it for easy comparison.
    # First convolutional layer.
    layer_conv1, weights_conv1 = \
        new_conv_layer(input=x_image,
                       num_input_channels=num_channels,
                       filter_size=5,
                       num_filters=16,
                       use_pooling=True)

    # Second convolutional layer.
    layer_conv2, weights_conv2 = \
        new_conv_layer(input=layer_conv1,
                       num_input_channels=16,
                       filter_size=5,
                       num_filters=36,
                       use_pooling=True)

    # Flatten layer.
    layer_flat, num_features = flatten_layer(layer_conv2)

    # First fully-connected layer.
    layer_fc1 = new_fc_layer(input=layer_flat,
                             num_inputs=num_features,
                             num_outputs=128,
                             use_relu=True)

    # Second fully-connected layer.
    layer_fc2 = new_fc_layer(input=layer_fc1,
                             num_inputs=128,
                             num_outputs=num_classes,
                             use_relu=False)

    # Predicted class-label.
    y_pred = tf.nn.softmax(layer_fc2)

    # Cross-entropy for the classification of each image.
    cross_entropy = \
        tf.nn.softmax_cross_entropy_with_logits(logits=layer_fc2,
                                                labels=y_true)

    # Loss aka. cost-measure.
    # This is the scalar value that must be minimized.
    loss = tf.reduce_mean(cross_entropy)複製代碼

PrettyTensor實現

這一節演示如何用PrettyTensor來實現一個相同的卷積神經網絡。

基本思想就是用一個PrettyTensor object封裝輸入張量x_image，它有一個添加新卷積層的幫助函數，以此來建立整個神經網絡。這有點像咱們以前實現的那些幫助函數，但它更簡單一些，由於PrettyTensor記錄每一層的輸入和輸出維度等等。

x_pretty = pt.wrap(x_image)複製代碼

如今咱們已經將輸入圖像裝到一個PrettyTensor的object中，再用幾行代碼就能夠添加捲積層和全鏈接層。

注意，在with代碼塊中，pt.defaults_scope(activation_fn=tf.nn.relu) 把 activation_fn=tf.nn.relu看成每一個的層參數，所以這些層都用到了 Rectified Linear Units (ReLU) 。defaults_scope使咱們能更方便地修改全部層的參數。

with pt.defaults_scope(activation_fn=tf.nn.relu):
    y_pred, loss = x_pretty.\
        conv2d(kernel=5, depth=16, name='layer_conv1').\
        max_pool(kernel=2, stride=2).\
        conv2d(kernel=5, depth=36, name='layer_conv2').\
        max_pool(kernel=2, stride=2).\
        flatten().\
        fully_connected(size=128, name='layer_fc1').\
        softmax_classifier(num_classes=num_classes, labels=y_true)複製代碼

就是這樣！如今咱們用幾行代碼就建立了一個徹底同樣的卷積神經網絡，若是直接用TensorFlow實現的話須要一大段很是複雜的代碼。

用PrettyTensor來代替TensorFlow，咱們能夠清楚地看到網絡的構造以及數據如何在網絡中流通。這讓咱們能夠專一於神經網絡的關鍵思想而不是底層的實現細節。它十分簡單優雅！

獲取權重

不幸的是，使用PrettyTensor時並不是全部的事都那麼優雅。

下面，咱們想要繪製出卷積層的權重。在用TensorFlow實現時，咱們本身建立了變量，因此能夠直接訪問它們。但使用PrettyTensor構造網絡時，全部的變量都是間接地由PrettyTensor建立。所以咱們不得不從TensorFlow中找回變量。

咱們用layer_conv1 和 layer_conv2表明兩個卷積層。這也叫變量做用域（不要與上面描述的defaults_scope混淆了）。PrettyTensor會自動給它爲每一個層建立的變量命名，所以咱們能夠經過層的做用域名稱和變量名來取得某一層的權重。

函數實現有點笨拙，由於咱們不得不用TensorFlow函數get_variable()，它是設計給其餘用途的，建立新的變量或重用現有變量。建立下面的幫助函數很簡單。

def get_weights_variable(layer_name):
    # Retrieve an existing variable named 'weights' in the scope
    # with the given layer_name.
    # This is awkward because the TensorFlow function was
    # really intended for another purpose.

    with tf.variable_scope(layer_name, reuse=True):
        variable = tf.get_variable('weights')

    return variable複製代碼

藉助這個幫助函數咱們能夠獲取變量。這些是TensorFlow的objects。你須要相似的操做來獲取變量的內容： contents = session.run(weights_conv1) ，下面會提到這個。

weights_conv1 = get_weights_variable(layer_name='layer_conv1')
weights_conv2 = get_weights_variable(layer_name='layer_conv2')複製代碼

優化方法

PrettyTensor給咱們提供了預測類型標籤(y_pred)以及一個須要最小化的損失度量，用來提高神經網絡分類圖片的能力。

PrettyTensor的文檔並無說明它的損失度量是用cross-entropy仍是其餘的。但如今咱們用AdamOptimizer來最小化損失。

優化過程並非在這裏執行。實際上，還沒計算任何東西，咱們只是往TensorFlow圖中添加了優化器，以便後續操做。

optimizer = tf.train.AdamOptimizer(learning_rate=1e-4).minimize(loss)複製代碼

性能度量

咱們須要另一些性能度量，來向用戶展現這個過程。

首先咱們從神經網絡輸出的y_pred中計算出預測的類別，它是一個包含10個元素的向量。類別數字是最大元素的索引。

y_pred_cls = tf.argmax(y_pred, dimension=1)複製代碼

而後建立一個布爾向量，用來告訴咱們每張圖片的真實類別是否與預測類別相同。

correct_prediction = tf.equal(y_pred_cls, y_true_cls)複製代碼

上面的計算先將布爾值向量類型轉換成浮點型向量，這樣子False就變成0，True變成1，而後計算這些值的平均數，以此來計算分類的準確度。

accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))複製代碼

運行TensorFlow

建立TensorFlow會話（session）

一旦建立了TensorFlow圖，咱們須要建立一個TensorFlow會話，用來運行圖。

session = tf.Session()複製代碼

初始化變量

咱們須要在開始優化weights和biases變量以前對它們進行初始化。

session.run(tf.global_variables_initializer())複製代碼

用來優化迭代的幫助函數

在訓練集中有50,000張圖。用這些圖像計算模型的梯度會花不少時間。所以咱們利用隨機梯度降低的方法，它在優化器的每次迭代裏只用到了一小部分的圖像。
若是內存耗盡致使電腦死機或變得很慢，你應該試着減小這些數量，但同時可能還須要更優化的迭代。

train_batch_size = 64複製代碼

函數執行了屢次的優化迭代來逐步地提高網絡層的變量。在每次迭代中，從訓練集中選擇一批新的數據，而後TensorFlow用這些訓練樣原本執行優化器。每100次迭代會打印出相關信息。

# Counter for total number of iterations performed so far.
total_iterations = 0

def optimize(num_iterations):
    # Ensure we update the global variable rather than a local copy.
    global total_iterations

    # Start-time used for printing time-usage below.
    start_time = time.time()

    for i in range(total_iterations,
                   total_iterations + num_iterations):

        # Get a batch of training examples.
        # x_batch now holds a batch of images and
        # y_true_batch are the true labels for those images.
        x_batch, y_true_batch = data.train.next_batch(train_batch_size)

        # Put the batch into a dict with the proper names
        # for placeholder variables in the TensorFlow graph.
        feed_dict_train = {x: x_batch,
                           y_true: y_true_batch}

        # Run the optimizer using this batch of training data.
        # TensorFlow assigns the variables in feed_dict_train
        # to the placeholder variables and then runs the optimizer.
        session.run(optimizer, feed_dict=feed_dict_train)

        # Print status every 100 iterations.
        if i % 100 == 0:
            # Calculate the accuracy on the training-set.
            acc = session.run(accuracy, feed_dict=feed_dict_train)

            # Message for printing.
            msg = "Optimization Iteration: {0:>6}, Training Accuracy: {1:>6.1%}"

            # Print it.
            print(msg.format(i + 1, acc))

    # Update the total number of iterations performed.
    total_iterations += num_iterations

    # Ending time.
    end_time = time.time()

    # Difference between start and end-times.
    time_dif = end_time - start_time

    # Print the time-usage.
    print("Time usage: " + str(timedelta(seconds=int(round(time_dif)))))複製代碼

用來繪製錯誤樣本的幫助函數

函數用來繪製測試集中被誤分類的樣本。

def plot_example_errors(cls_pred, correct):
    # This function is called from print_test_accuracy() below.

    # cls_pred is an array of the predicted class-number for
    # all images in the test-set.

    # correct is a boolean array whether the predicted class
    # is equal to the true class for each image in the test-set.

    # Negate the boolean array.
    incorrect = (correct == False)

    # Get the images from the test-set that have been
    # incorrectly classified.
    images = data.test.images[incorrect]

    # Get the predicted classes for those images.
    cls_pred = cls_pred[incorrect]

    # Get the true classes for those images.
    cls_true = data.test.cls[incorrect]

    # Plot the first 9 images.
    plot_images(images=images[0:9],
                cls_true=cls_true[0:9],
                cls_pred=cls_pred[0:9])複製代碼

繪製混淆（confusion）矩陣的幫助函數

def plot_confusion_matrix(cls_pred):
    # This is called from print_test_accuracy() below.

    # cls_pred is an array of the predicted class-number for
    # all images in the test-set.

    # Get the true classifications for the test-set.
    cls_true = data.test.cls

    # Get the confusion matrix using sklearn.
    cm = confusion_matrix(y_true=cls_true,
                          y_pred=cls_pred)

    # Print the confusion matrix as text.
    print(cm)

    # Plot the confusion matrix as an image.
    plt.matshow(cm)

    # Make various adjustments to the plot.
    plt.colorbar()
    tick_marks = np.arange(num_classes)
    plt.xticks(tick_marks, range(num_classes))
    plt.yticks(tick_marks, range(num_classes))
    plt.xlabel('Predicted')
    plt.ylabel('True')

    # Ensure the plot is shown correctly with multiple plots
    # in a single Notebook cell.
    plt.show()複製代碼

展現性能的幫助函數

函數用來打印測試集上的分類準確度。

爲測試集上的全部圖片計算分類會花費一段時間，所以咱們直接用這個函數來調用上面的結果，這樣就不用每次都從新計算了。

這個函數可能會佔用不少電腦內存，這也是爲何將測試集分紅更小的幾個部分。若是你的電腦內存比較小或死機了，就要試着下降batch-size。

# Split the test-set into smaller batches of this size.
test_batch_size = 256

def print_test_accuracy(show_example_errors=False, show_confusion_matrix=False):

    # Number of images in the test-set.
    num_test = len(data.test.images)

    # Allocate an array for the predicted classes which
    # will be calculated in batches and filled into this array.
    cls_pred = np.zeros(shape=num_test, dtype=np.int)

    # Now calculate the predicted classes for the batches.
    # We will just iterate through all the batches.
    # There might be a more clever and Pythonic way of doing this.

    # The starting index for the next batch is denoted i.
    i = 0

    while i < num_test:
        # The ending index for the next batch is denoted j.
        j = min(i + test_batch_size, num_test)

        # Get the images from the test-set between index i and j.
        images = data.test.images[i:j, :]

        # Get the associated labels.
        labels = data.test.labels[i:j, :]

        # Create a feed-dict with these images and labels.
        feed_dict = {x: images,
                     y_true: labels}

        # Calculate the predicted class using TensorFlow.
        cls_pred[i:j] = session.run(y_pred_cls, feed_dict=feed_dict)

        # Set the start-index for the next batch to the
        # end-index of the current batch.
        i = j

    # Convenience variable for the true class-numbers of the test-set.
    cls_true = data.test.cls

    # Create a boolean array whether each image is correctly classified.
    correct = (cls_true == cls_pred)

    # Calculate the number of correctly classified images.
    # When summing a boolean array, False means 0 and True means 1.
    correct_sum = correct.sum()

    # Classification accuracy is the number of correctly classified
    # images divided by the total number of images in the test-set.
    acc = float(correct_sum) / num_test

    # Print the accuracy.
    msg = "Accuracy on Test-Set: {0:.1%} ({1} / {2})"
    print(msg.format(acc, correct_sum, num_test))

    # Plot some examples of mis-classifications, if desired.
    if show_example_errors:
        print("Example errors:")
        plot_example_errors(cls_pred=cls_pred, correct=correct)

    # Plot the confusion matrix, if desired.
    if show_confusion_matrix:
        print("Confusion Matrix:")
        plot_confusion_matrix(cls_pred=cls_pred)複製代碼

優化以前的性能

測試集上的準確度很低，這是因爲模型只作了初始化，並沒作任何優化，因此它只是對圖像作隨機分類。

print_test_accuracy()複製代碼

Accuracy on Test-Set: 9.1% (909 / 10000)複製代碼

1次迭代後的性能

作了一次優化後，此時優化器的學習率很低，性能其實並無多大提高。

optimize(num_iterations=1)複製代碼

Optimization Iteration: 1, Training Accuracy: 6.2%
Time usage: 0:00:00

print_test_accuracy()複製代碼

Accuracy on Test-Set: 8.9% (892 / 10000)

100次迭代優化後的性能

100次優化迭代以後，模型顯著地提高了分類的準確度。

optimize(num_iterations=99) # We already performed 1 iteration above.複製代碼

Time usage: 0:00:00

print_test_accuracy(show_example_errors=True)複製代碼

Accuracy on Test-Set: 83.9% (8393 / 10000)
Example errors:

1000次優化迭代後的性能

1000次優化迭代以後，模型在測試集上的準確度超過了90%。

optimize(num_iterations=900) # We performed 100 iterations above.複製代碼

Optimization Iteration: 101, Training Accuracy: 93.8%
Optimization Iteration: 201, Training Accuracy: 89.1%
Optimization Iteration: 301, Training Accuracy: 85.9%
Optimization Iteration: 401, Training Accuracy: 87.5%
Optimization Iteration: 501, Training Accuracy: 92.2%
Optimization Iteration: 601, Training Accuracy: 95.3%
Optimization Iteration: 701, Training Accuracy: 95.3%
Optimization Iteration: 801, Training Accuracy: 90.6%
Optimization Iteration: 901, Training Accuracy: 98.4%
Time usage: 0:00:03

print_test_accuracy(show_example_errors=True)複製代碼

Accuracy on Test-Set: 96.3% (9634 / 10000)
Example errors:

10,000次優化迭代後的性能

通過10,000次優化迭代後，測試集上的分類準確率高達99%。

optimize(num_iterations=9000) # We performed 1000 iterations above.複製代碼

Optimization Iteration: 1001, Training Accuracy: 98.4%
Optimization Iteration: 1101, Training Accuracy: 95.3%
Optimization Iteration: 1201, Training Accuracy: 98.4%
Optimization Iteration: 1301, Training Accuracy: 96.9%
Optimization Iteration: 1401, Training Accuracy: 100.0%
Optimization Iteration: 1501, Training Accuracy: 95.3%
Optimization Iteration: 1601, Training Accuracy: 96.9%
Optimization Iteration: 1701, Training Accuracy: 96.9%
Optimization Iteration: 1801, Training Accuracy: 98.4%
Optimization Iteration: 1901, Training Accuracy: 96.9%
Optimization Iteration: 2001, Training Accuracy: 98.4%
Optimization Iteration: 2101, Training Accuracy: 95.3%
Optimization Iteration: 2201, Training Accuracy: 98.4%
Optimization Iteration: 2301, Training Accuracy: 98.4%
Optimization Iteration: 2401, Training Accuracy: 98.4%
Optimization Iteration: 2501, Training Accuracy: 93.8%
Optimization Iteration: 2601, Training Accuracy: 98.4%
Optimization Iteration: 2701, Training Accuracy: 98.4%
Optimization Iteration: 2801, Training Accuracy: 95.3%
Optimization Iteration: 2901, Training Accuracy: 98.4%
Optimization Iteration: 3001, Training Accuracy: 98.4%
Optimization Iteration: 3101, Training Accuracy: 100.0%
Optimization Iteration: 3201, Training Accuracy: 96.9%
Optimization Iteration: 3301, Training Accuracy: 100.0%
Optimization Iteration: 3401, Training Accuracy: 98.4%
Optimization Iteration: 3501, Training Accuracy: 96.9%
Optimization Iteration: 3601, Training Accuracy: 98.4%
Optimization Iteration: 3701, Training Accuracy: 96.9%
Optimization Iteration: 3801, Training Accuracy: 100.0%
Optimization Iteration: 3901, Training Accuracy: 98.4%
Optimization Iteration: 4001, Training Accuracy: 96.9%
Optimization Iteration: 4101, Training Accuracy: 98.4%
Optimization Iteration: 4201, Training Accuracy: 100.0%
Optimization Iteration: 4301, Training Accuracy: 100.0%
Optimization Iteration: 4401, Training Accuracy: 100.0%
Optimization Iteration: 4501, Training Accuracy: 100.0%
Optimization Iteration: 4601, Training Accuracy: 98.4%
Optimization Iteration: 4701, Training Accuracy: 96.9%
Optimization Iteration: 4801, Training Accuracy: 95.3%
Optimization Iteration: 4901, Training Accuracy: 100.0%
Optimization Iteration: 5001, Training Accuracy: 96.9%
Optimization Iteration: 5101, Training Accuracy: 100.0%
Optimization Iteration: 5201, Training Accuracy: 98.4%
Optimization Iteration: 5301, Training Accuracy: 98.4%
Optimization Iteration: 5401, Training Accuracy: 100.0%
Optimization Iteration: 5501, Training Accuracy: 98.4%
Optimization Iteration: 5601, Training Accuracy: 96.9%
Optimization Iteration: 5701, Training Accuracy: 100.0%
Optimization Iteration: 5801, Training Accuracy: 96.9%
Optimization Iteration: 5901, Training Accuracy: 100.0%
Optimization Iteration: 6001, Training Accuracy: 98.4%
Optimization Iteration: 6101, Training Accuracy: 98.4%
Optimization Iteration: 6201, Training Accuracy: 98.4%
Optimization Iteration: 6301, Training Accuracy: 98.4%
Optimization Iteration: 6401, Training Accuracy: 100.0%
Optimization Iteration: 6501, Training Accuracy: 100.0%
Optimization Iteration: 6601, Training Accuracy: 100.0%
Optimization Iteration: 6701, Training Accuracy: 100.0%
Optimization Iteration: 6801, Training Accuracy: 96.9%
Optimization Iteration: 6901, Training Accuracy: 100.0%
Optimization Iteration: 7001, Training Accuracy: 100.0%
Optimization Iteration: 7101, Training Accuracy: 100.0%
Optimization Iteration: 7201, Training Accuracy: 100.0%
Optimization Iteration: 7301, Training Accuracy: 96.9%
Optimization Iteration: 7401, Training Accuracy: 100.0%
Optimization Iteration: 7501, Training Accuracy: 100.0%
Optimization Iteration: 7601, Training Accuracy: 96.9%
Optimization Iteration: 7701, Training Accuracy: 100.0%
Optimization Iteration: 7801, Training Accuracy: 100.0%
Optimization Iteration: 7901, Training Accuracy: 100.0%
Optimization Iteration: 8001, Training Accuracy: 98.4%
Optimization Iteration: 8101, Training Accuracy: 100.0%
Optimization Iteration: 8201, Training Accuracy: 100.0%
Optimization Iteration: 8301, Training Accuracy: 100.0%
Optimization Iteration: 8401, Training Accuracy: 100.0%
Optimization Iteration: 8501, Training Accuracy: 98.4%
Optimization Iteration: 8601, Training Accuracy: 100.0%
Optimization Iteration: 8701, Training Accuracy: 100.0%
Optimization Iteration: 8801, Training Accuracy: 100.0%
Optimization Iteration: 8901, Training Accuracy: 100.0%
Optimization Iteration: 9001, Training Accuracy: 98.4%
Optimization Iteration: 9101, Training Accuracy: 98.4%
Optimization Iteration: 9201, Training Accuracy: 100.0%
Optimization Iteration: 9301, Training Accuracy: 100.0%
Optimization Iteration: 9401, Training Accuracy: 98.4%
Optimization Iteration: 9501, Training Accuracy: 100.0%
Optimization Iteration: 9601, Training Accuracy: 100.0%
Optimization Iteration: 9701, Training Accuracy: 100.0%
Optimization Iteration: 9801, Training Accuracy: 98.4%
Optimization Iteration: 9901, Training Accuracy: 100.0%
Time usage: 0:00:27

print_test_accuracy(show_example_errors=True,
                    show_confusion_matrix=True)複製代碼

Accuracy on Test-Set: 98.8% (9881 / 10000)
Example errors:

Confusion Matrix:
[[ 975 0 0 0 0 0 1 1 3 0]
[ 0 1127 2 0 0 0 1 2 3 0]
[ 2 2 1019 1 1 0 1 2 4 0]
[ 0 0 0 1005 0 1 0 1 3 0]
[ 0 0 0 0 977 0 1 0 1 3]
[ 2 0 0 13 0 870 1 0 6 0]
[ 5 2 0 0 1 3 943 0 4 0]
[ 0 2 8 2 1 0 0 1007 1 7]
[ 2 0 2 3 1 1 0 0 964 1]
[ 0 2 0 4 5 1 0 1 2 994]]

權重和層的可視化

當咱們直接用TensorFlow來實現卷積神經網絡時，能夠很容易地畫出卷積權重和不一樣層的輸出圖像。當使用PrettyTensor的時候，咱們也能夠經過上面提到過的方法取得權重，但咱們沒法簡單獲得卷積層的輸出（圖像）。所以下面只繪製了權重。

繪製卷積權重的幫助函數

def plot_conv_weights(weights, input_channel=0):
    # Assume weights are TensorFlow ops for 4-dim variables
    # e.g. weights_conv1 or weights_conv2.

    # Retrieve the values of the weight-variables from TensorFlow.
    # A feed-dict is not necessary because nothing is calculated.
    w = session.run(weights)

    # Get the lowest and highest values for the weights.
    # This is used to correct the colour intensity across
    # the images so they can be compared with each other.
    w_min = np.min(w)
    w_max = np.max(w)

    # Number of filters used in the conv. layer.
    num_filters = w.shape[3]

    # Number of grids to plot.
    # Rounded-up, square-root of the number of filters.
    num_grids = math.ceil(math.sqrt(num_filters))

    # Create figure with a grid of sub-plots.
    fig, axes = plt.subplots(num_grids, num_grids)

    # Plot all the filter-weights.
    for i, ax in enumerate(axes.flat):
        # Only plot the valid filter-weights.
        if i<num_filters:
            # Get the weights for the i'th filter of the input channel.
            # See new_conv_layer() for details on the format
            # of this 4-dim tensor.
            img = w[:, :, input_channel, i]

            # Plot image.
            ax.imshow(img, vmin=w_min, vmax=w_max,
                      interpolation='nearest', cmap='seismic')

        # Remove ticks from the plot.
        ax.set_xticks([])
        ax.set_yticks([])

    # Ensure the plot is shown correctly with multiple plots
    # in a single Notebook cell.
    plt.show()複製代碼

卷積層 1

如今繪製第一個卷積層的濾波權重。

其中正值權重是紅色的，負值爲藍色。

plot_conv_weights(weights=weights_conv1)複製代碼

卷積層 2

如今繪製第二個卷積層的濾波權重。

第一個卷積層有16個輸出通道，表明着第二個卷基層有16個輸入。第二個卷積層的每一個輸入通道也有一些權重濾波。咱們先繪製第一個通道的權重濾波。

一樣的，正值是紅色，負值是藍色。

plot_conv_weights(weights=weights_conv2, input_channel=0)複製代碼

第二個卷積層共有16個輸入通道，咱們能夠一樣地畫出15張其餘濾波權重圖像。這裏咱們再畫一下第二個通道的圖像。

plot_conv_weights(weights=weights_conv2, input_channel=1)複製代碼

關閉TensorFlow會話

如今咱們已經用TensorFlow完成了任務，關閉session，釋放資源。

# This has been commented out in case you want to modify and experiment
# with the Notebook without having to restart it.
# session.close()複製代碼

總結

相比直接使用TensorFlow，PrettyTensor能夠用更簡單的代碼來實現神經網絡。這使你可以專一於本身的想法而不是底層的實現細節。它讓代碼更易於理解，也減小犯錯的可能。

然而，PrettyTensor中有一些矛盾和笨拙的設計，它的文檔簡短而又使人疑惑，也不易於學習。但願將來會有所改進（本文寫於2016七月）。

還有一些PrettyTensor的替代品，包括TFLearn和Keras。

練習

下面使一些可能會讓你提高TensorFlow技能的一些建議練習。爲了學習如何更合適地使用TensorFlow，實踐經驗是很重要的。

在你對這個Notebook進行修改以前，可能須要先備份一下。

將全部層的激活函數改爲sigmod。
在一些層中使用sigmod，一些層中使用relu。這裏能用defaults_scope嗎？
在全部層裏使用12loss。而後試着只在某些層裏使用這個。
用PrettyTensor的reshape函數代替TensorFlow的。其中某一個會更好嗎？
在全鏈接層後面添加一個dropout-layer。若是你在訓練和測試的時候想要一個不一樣的keep_prob，就須要在feed-dict中設置一個placeholder變量。
用stride=2來代替 2x2 max-pooling層。分類準確率會有所不一樣麼？你屢次優化它們以後呢？差別是隨機的，你如何度量是否真實存在差別呢？在卷積層中使用max-pooling和stride的優缺點是什麼？
改變層的參數，好比kernel、depth、size等等。耗費的時間以及分類準確率有什麼差異？
添加或刪除某些卷積層和全鏈接層。
你設計的表現良好的最簡網絡是什麼？
取回卷積層的bias-values並打印出來。參考一下get_weights_variable()的實現。
不看源碼，本身重寫程序。
向朋友解釋程序如何工做。