1.4 神經網絡入門-數據處理與模型圖構建

1.4 數據處理與模型圖構建

• transflow 搭建 : www.tensorflow.org/install/ins…

• 使用的是cifar-10 的數據集 www.cs.toronto.edu/~kriz/cifar…

  The CIFAR-10 dataset consists of 60000 32x32 colour images in 10 classes, with 6000 images per class. There are 50000 training images and 10000 test images.

  CIFAR-10 下載下來的python版本文件目錄結構以下

  (deeplearning-0jfGJJsa) ~/project/pycharm/deeplearning/01_nn ᐅ tree cifar-10-batches-py
  cifar-10-batches-py
  ├── batches.meta
  ├── data_batch_1 # 一共5個batch的訓練數據集，每一個batch中有10000張圖片和對應的數據
  ├── data_batch_2
  ├── data_batch_3
  ├── data_batch_4
  ├── data_batch_5
  ├── readme.html
  └── test_batch # 測試數據集
  
  0 directories, 8 files
  複製代碼

• 關於jupyternotebook修改默認環境的文章：www.jianshu.com/p/f70ea020e…

• 直觀的顯示一張圖片

  • 導入數據集

  import pickle
  import numpy as np
  import os
  
  CIFAR_DIR = './cifar-10-batches-py'
  print(os.listdir(CIFAR_DIR))
  複製代碼

  ['data_batch_1', 'readme.html', 'batches.meta', 'data_batch_2', 'data_batch_5', 'test_batch', 'data_batch_4', 'data_batch_3']
  複製代碼

  with open(os.path.join(CIFAR_DIR, "data_batch_1"), 'rb') as f:
      data = pickle.load(f, encoding='bytes')
      print(type(data))
      print(data.keys())
      print(type(data[b'data']))
      print(type(data[b'labels']))
      print(type(data[b'batch_label']))
      print(type(data[b'filenames']))
      print(data[b'data'].shape) # 32 * 32 （像素點）* 3(rbg三通道) # RR-GG-BB
      print(data[b'data'][0:2])
      print(data[b'labels'][0:2])
      print(data[b'batch_label'])
      print(data[b'filenames'][0:2])
  複製代碼

  <class 'dict'>
  dict_keys([b'batch_label', b'labels', b'data', b'filenames'])
  <class 'numpy.ndarray'>
  <class 'list'>
  <class 'bytes'>
  <class 'list'>
  (10000, 3072)
  [[ 59  43  50 ... 140  84  72]
   [154 126 105 ... 139 142 144]]
  [6, 9]
  b'training batch 1 of 5'
  [b'leptodactylus_pentadactylus_s_000004.png', b'camion_s_000148.png']
  複製代碼

  • 顯示一張圖片

  image_arr = data[b'data'][100]
  image_arr = image_arr.reshape((3,32,32)) # 須要32，32，3
  image_arr = image_arr.transpose((1,2,0))
  
  from matplotlib.pyplot import imshow
  
  imshow(image_arr)
  複製代碼

  <matplotlib.image.AxesImage at 0x12311e668>
  複製代碼

  

• 模型圖構建

  import tensorflow as tf
  import pickle
  import numpy as np
  import os
  
  CIFAR_DIR = './cifar-10-batches-py'
  print(os.listdir(CIFAR_DIR))
  
  def load_data(filename):
      """read data from data file."""
      with open(filename, 'rb') as f:
          data = pickle.load(f, 'bytes')
          return data[b'data'], data[b'labels']
  
  # placeholder 佔位符，能夠表明一個變量，能夠用來構建計算圖，有數據來的時候就把數據傳入
  # None 表明輸入的樣本數目是不肯定的，3072 是變量的維度
  x = tf.placeholder(tf.float32, [None, 3072]) 
  y = tf.placeholder(tf.int64, [None]) # 只有一個維度就省略了
  
  # get_variable 若是已經定義了則使用，不然使用指定方式定義
  # 'w':變量名
  # [x.get_shape()[-1],1]: 指定變量的維度
  # initializer: 初始化變量的方式
  w = tf.get_variable('w', [x.get_shape()[-1],1], 
                     initializer = tf.random_normal_initializer(0, 1)) 
  b = tf.get_variable('b', [1], 
                     initializer = tf.constant_initializer(0.0))
  
  # matmul 矩陣乘法 
  # x (None,3072) w (3072,1) b(3072,1)
  # y_ = [None,3072]*[3072,1] + [3072,1] = [None,1]
  y_ = tf.matmul(x, w) + b
  # 激活函數 (None,1)
  p_y_1 = tf.nn.sigmoid(y_)
  
  # (None,1)
  y_reshaped = tf.reshape(y, (-1,1))
  y_reshaped_float = tf.cast(y_reshaped, tf.float32)
  loss = tf.reduce_mean(tf.square(y_reshaped_float - p_y_1))
  
  # bool
  predict = p_y_1 > 0.5
  # [1,0,1,1,0,0,0]
  correct_prediction = tf.equal(tf.cast(predict,tf.int64), y_reshaped)
  # 3/7
  accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float64))
  
  with tf.name_scope('train_op'):
      # AdamOptimizer 是梯度降低的一個變種，minimize指定在哪一個變量上作
      train_op = tf.train.AdamOptimizer(1e-3).minimize(loss)
  
  複製代碼