2019.12.14

一、tensorflow

1.結果的可視化

莫煩大佬的代碼如下：

from __future__ import  print_function
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt


def add_layer(inputs, in_size, out_size, activation_function=None):
    # 增加一層隱藏層，返回隱藏層的輸出值
    Weights = tf.Variable(tf.random_normal([in_size, out_size]))
    biases = tf.Variable(tf.zeros([1, out_size])+0.1) # 加0.1使得初始化片偏差不爲零
    Wx_plus_b = tf.matmul(inputs, Weights) + biases
    if activation_function is None:
        outputs = Wx_plus_b
    else:
        outputs = activation_function(Wx_plus_b)
    return outputs

# Make up some real data
x_data = np.linspace(-1,1,300)[:, np.newaxis]
noise = np.random.normal(0, 0.05, x_data.shape)
y_data = np.square(x_data) - 0.5 + noise

# define placeholder for inputs for network
xs = tf.placeholder(tf.float32, [None, 1])
ys = tf.placeholder(tf.float32, [None, 1])

# add hidden layer
l1 = add_layer(xs, 1, 10, activation_function=tf.nn.relu)

# add output layer
prediction = add_layer(l1, 10, 1, activation_function=None)

# define the error between prediction and real data
loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys - prediction), reduction_indices=[1]))
train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)

# initialize_all_variables()
init = tf.global_variables_initializer()

sess = tf.Session()
sess.run(init)

# plot the real data
fig = plt.figure()
ax = fig.add_subplot(1, 1, 1)
ax.scatter(x_data, y_data)
plt.ion()
plt.show()

# 訓練2000次
for i in range(2000):
    sess.run(train_step, feed_dict={xs: x_data, ys: y_data})
    if i % 50 == 0:
        # to visualize the result and improvement
        try:
            ax.lines.remove(lines[0])
        except Exception:
            pass
        prediction_value = sess.run(prediction, feed_dict={xs: x_data})
        # plot the prediction
        lines = ax.plot(x_data, prediction_value, '-r', lw=5)
        plt.pause(1)

對以上代碼有如下筆記：
1.plt.ion()：在plt.show()之後，程序會暫停到那兒，並不會繼續執行下去。使用plt.ion()這個函數，使matplotlib的顯示模式轉換爲交互（interactive）模式。即使在腳本中遇到plt.show()，代碼還是會繼續執行。具體參考這篇文章。
2.try except：屬於python的異常處理機制之一，具體參考這篇文章。

2.tensorboard簡單使用

同煩大佬的代碼;

from __future__ import  print_function
import tensorflow as tf


def add_layer(inputs, in_size, out_size, activation_function=None):
    # 增加一層隱藏層，返回隱藏層的輸出值
    with tf.name_scope('layer'):
        with tf.name_scope('weights'):
            Weights = tf.Variable(tf.random_normal([in_size, out_size]))
        with tf.name_scope('biases'):
            biases = tf.Variable(tf.zeros([1, out_size])+0.1) # 加0.1使得初始化片偏差不爲零
        with tf.name_scope('Wx_plus_b'):
            Wx_plus_b = tf.matmul(inputs, Weights) + biases
        if activation_function is None:
            outputs = Wx_plus_b
        else:
            outputs = activation_function(Wx_plus_b)
        return outputs
    

# define placeholder for inputs for network
with tf.name_scope('inputs'):
    xs = tf.placeholder(tf.float32, [None, 1])
    ys = tf.placeholder(tf.float32, [None, 1])

# add hidden layer
l1 = add_layer(xs, 1, 10, activation_function=tf.nn.relu)

# add output layer
prediction = add_layer(l1, 10, 1, activation_function=None)

# define the error between prediction and real data
with tf.name_scope('loss'):
    loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys - prediction), reduction_indices=[1]))
with tf.name_scope('train'):
    train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)

# initialize_all_variables()
init = tf.global_variables_initializer()

sess = tf.Session()

# tf.train.SummaryWriter soon be deprecated, use following
writer = tf.summary.FileWriter("logs/", sess.graph)

sess.run(init)

打開tensorboard的步驟：

1.首先運行代碼生成log文件之後，activate虛擬環境。

2.然後，在terminal中cd到tensorboard所在的文件夾下。

3.再運行tensorboard --logdir logs即可。

4.複製得到的這個鏈接，再瀏覽器中打開即可。

··········································································································
實踐證明上述方法目前來看只是能獲得一個鏈接而已，但是似乎並沒有看到和莫煩大佬視頻中類似的效果。並且第二段代碼如下（雖說失敗了，但是先記錄一下，之後再看）：
（之後再看點開，解決方法就可以）

from __future__ import  print_function
import tensorflow as tf
import numpy as np



def add_layer(inputs, in_size, out_size, n_layer, activation_function=None):
    # 增加一層隱藏層，返回隱藏層的輸出值
    layer_name = 'layer %s' % n_layer
    with tf.name_scope('layer'):
        with tf.name_scope('weights'):
            Weights = tf.Variable(tf.random.normal([in_size, out_size]), name='W')
            tf.compat.v1.summary.histogram(layer_name + 'weights', Weights)
        with tf.name_scope('biases'):
            biases = tf.Variable(tf.zeros([1, out_size]) + 0.1, name='b')  # 加0.1使得初始化片偏差不爲零
            tf.compat.v1.summary.histogram(layer_name + '/biases', biases)
        with tf.name_scope('Wx_plus_b'):
            Wx_plus_b = tf.matmul(inputs, Weights) + biases
        if activation_function is None:
            outputs = Wx_plus_b
        else:
            outputs = activation_function(Wx_plus_b, )
        tf.compat.v1.summary.histogram(layer_name + '/outputs', outputs)
    return outputs


# Make up some real data
x_data = np.linspace(-1, 1, 300)[:, np.newaxis]
noise = np.random.normal(0, 0.05, x_data.shape)
y_data = np.square(x_data) - 0.5 + noise

# define placeholder for inputs for network
with tf.name_scope('inputs'):
    xs = tf.compat.v1.placeholder(tf.float32, [None, 1], name='x_input')
    ys = tf.compat.v1.placeholder(tf.float32, [None, 1], name='y_input')

# add hidden layer
l1 = add_layer(xs, 1, 10, n_layer=1, activation_function=tf.nn.relu)

# add output layer
prediction = add_layer(l1, 10, 1, n_layer=2, activation_function=None)

# define the error between prediction and real data
with tf.name_scope('loss'):
    loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys - prediction), reduction_indices=[1]))
    tf.compat.v1.summary.scalar('loss', loss)

with tf.name_scope('train'):
    train_step = tf.compat.v1.train.GradientDescentOptimizer(0.1).minimize(loss)

sess = tf.compat.v1.Session()
merged = tf.compat.v1.summary.merge_all()

# tf.train.SummaryWriter soon be deprecated, use following
writer = tf.compat.v1.summary.FileWriter("logs/", sess.graph)

# initialize_all_variables()
init = tf.compat.v1.global_variables_initializer()
sess.run(init)

# 訓練2000次
for i in range(2000):
    sess.run(train_step, feed_dict={xs: x_data, ys: y_data})
    if i % 50 == 0:
        result = sess.run(merged, feed_dict={xs: x_data, ys: y_data})
        writer.add_summary(result, i)

二、C++

1.指針（pointer）和引用（reference）的區別

指針是一個變量，只不過這個變量存儲的是一個地址，指向內存的一個存儲單元；而引用跟原來的變量實質上是同一個東西，只不過是原變量的一個別名而已。具體參考這篇文章。

2.明確堆（heap）和棧（stack）的區別

heap：是由new之類函數分配的空間所在地，需要通過delete釋放。地址是由低向高增長的。
stack：是自動分配變量，以及函數調用的時候所使用的一些空間。地址是由高向低減少的。

近期學習總結：

1.C++可以:

按照北大mooc所講順序，看入門書籍，當看書喫力可以結合視頻，互補學習。

2.強化學習可以繼續按照：

1.學習tensorflow（學到Saver那節先）。
2.運行《python強化學習實戰》六、七章代碼。
3.then：進行DQN（莫煩視頻and兩本書）。