1.4 神經網路入門-資料處理與模型圖構建

weixin_33861800發表於2019-01-26
神經網路模型

1.4 資料處理與模型圖構建

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

  • 使用的是cifar-10 的資料集 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版本檔案目錄結構如下

    (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的訓練資料集，每個batch中有10000張圖片和對應的資料
├── data_batch_2
├── data_batch_3
├── data_batch_4
├── data_batch_5
├── readme.html
└── test_batch # 測試資料集

0 directories, 8 files
複製程式碼

  • 關於jupyternotebook修改預設環境的文章：www.jianshu.com/p/f70ea020e…

  • 直觀的顯示一張圖片

    • 匯入資料集
    import pickle
import numpy as np
import os

CIFAR_DIR = './cifar-10-batches-py'
print(os.listdir(CIFAR_DIR))
複製程式碼
    ['data_batch_1', 'readme.html', 'batches.meta', 'data_batch_2', 'data_batch_5', 'test_batch', 'data_batch_4', 'data_batch_3']
複製程式碼
    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 （畫素點）* 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])
複製程式碼
    <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']
複製程式碼
    • 顯示一張圖片
    image_arr = data[b'data'][100]
image_arr = image_arr.reshape((3,32,32)) # 需要32，32，3
image_arr = image_arr.transpose((1,2,0))

from matplotlib.pyplot import imshow

imshow(image_arr)
複製程式碼
    <matplotlib.image.AxesImage at 0x12311e668>
複製程式碼

  • 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，可以代表一個變數，可以用來構建計算圖，有資料來的時候就把資料傳入
# None 代表輸入的樣本數目是不確定的，3072 是變數的維度
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 如果已經定義了則使用，否則使用指定方式定義
# 'w':變數名
# [x.get_shape()[-1],1]: 指定變數的維度
# initializer: 初始化變數的方式
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
# 啟用函式 (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 是梯度下降的一個變種，minimize指定在哪個變數上做
    train_op = tf.train.AdamOptimizer(1e-3).minimize(loss)

複製程式碼

相關文章