“深度学习”学习日记。神经网络的批处理

2023.1.7

昨天学习的神经网络的推理处理中的predict函数中的x的形状是一个有784个元素的一维数组，即代表一张图片，而今天学习的批处理的过程中，x数组的形状是“n维”每维784个元素（即一个n×784的矩阵）。在这里每一个x数组，代表一“批”数据就有“n张”图片，这样处理数据就称为批处理，对计算集的运算有极大好处，大幅度缩短处理时间。

# predict()函数以numpy数组的形式输出各个标签的对应的概率
def predict(network, x):
    W1, W2, W3 = network['W1'], network['W2'], network['W3']
    b1, b2, b3 = network['b1'], network['b2'], network['b3']

    a1 = np.dot(x, W1) + b1
    z1 = sigmoid(a1)
    a2 = np.dot(z1, W2) + b2
    z2 = sigmoid(a2)
    a3 = np.dot(z2, W3) + b3
    y = softmax(a3)  # 输出层设计 分类问题 通过线性代数的运算，得到符合我们需要的10个输出层
    print(x.shape)  # (784,)
    print(W1.shape)  # (784, 50)
    print(W2.shape)  # (50, 100)
    print(W3.shape)  # (100, 10)
    print("y的值")
    print(y, '\n')

    return y

主要的区别在这里：

首先先介绍一下range( )函数，

如果range( )函数被指定指定为range(start，end)，他会生成一个由start到end-1的一个列表

如果函数range( )被指定为range(start，end，step)并且三个参数为整数时，则列表生成下一个元素增加step的指定值

print(list(range(0, 10)))
print(list(range(0, 10, 2)))

# [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]
# [0, 2, 4, 6, 8]

 

 逐步解释代码：

x_batch = x[i:i + batch_size] 取出从i到i+batch_size之间的数据；

p = np.argmax(y_batch, axis=1)获取最大值的索引（下标），axis=1表示沿着第1维的方向进行，在矩阵（二维数组）中，第0维是列方向，第1维是行方向

在第一次处理中, x_batch=x[0:100];在第二次处理中, x_batch=x[100:200]............这样一批可以处理100张图片从而可以达到缩短运行时间的效果

x, t = get_data()
print("x的值", x, '\n', "t的值", t, '\n')
network = init_network()
batch_size = 100
accuracy_cnt = 0

for i in range(0, len(x), batch_size):
    x_batch = x[i:i + batch_size]
    y_batch = predict(network, x_batch)
    p = np.argmax(y_batch, axis=1)
    accuracy_cnt += np.sum(p == t[i:i + batch_size])

print("Accuracy:" + str(float(accuracy_cnt) / len(x)))

完整代码：

import numpy as np
import sys, os
from dataset.mnist import load_mnist
import pickle

sys.path.append(os.pardir)


def get_data():
    (x_train, t_train), (x_test, t_test) = load_mnist(normalize=True, flatten=True, one_hot_label=False)
    return x_test, t_test


def init_network():
    with open("sample_weight.pkl", 'rb') as f:
        network = pickle.load(f)
    return network


def predict(network, x):
    W1, W2, W3 = network['W1'], network['W2'], network['W3']
    b1, b2, b3 = network['b1'], network['b2'], network['b3']

    a1 = np.dot(x, W1) + b1
    z1 = sigmoid(a1)
    a2 = np.dot(z1, W2) + b2
    z2 = sigmoid(a2)
    a3 = np.dot(z2, W3) + b3
    y = softmax(a3)
    # print(x.shape)
    # print(W1.shape)
    # print(W2.shape)
    # print(W3.shape)
    # print("y的值")
    # print(y, '\n')

    return y


def sigmoid(x):
    return 1 / (1 + np.exp(-x))


def softmax(x):
    if x.ndim == 2:
        x = x.T
        x = x - np.max(x, axis=0)
        y = np.exp(x) / np.sum(np.exp(x), axis=0)
        return y.T

    x = x - np.max(x)
    return np.exp(x) / np.sum(np.exp(x))


x, t = get_data()
# print("x的值", x, '\n', "t的值", t, '\n')
network = init_network()
batch_size = 100
accuracy_cnt = 0

for i in range(0, len(x), batch_size):
    x_batch = x[i:i + batch_size]
    y_batch = predict(network, x_batch)
    p = np.argmax(y_batch, axis=1)
    accuracy_cnt += np.sum(p == t[i:i + batch_size])

print("Accuracy:" + str(float(accuracy_cnt) / len(x)))

MNIST的数据代入参考：

# coding: utf-8
try:
    import urllib.request
except ImportError:
    raise ImportError('You should use Python 3.x')
import os.path
import gzip
import pickle
import os
import numpy as np

url_base = 'http://yann.lecun.com/exdb/mnist/'
key_file = {
    'train_img': 'train-images-idx3-ubyte.gz',
    'train_label': 'train-labels-idx1-ubyte.gz',
    'test_img': 't10k-images-idx3-ubyte.gz',
    'test_label': 't10k-labels-idx1-ubyte.gz'
}

dataset_dir = os.path.dirname(os.path.abspath(__file__))
save_file = dataset_dir + "/mnist.pkl"

train_num = 60000
test_num = 10000
img_dim = (1, 28, 28)
img_size = 784


def _download(file_name):
    file_path = dataset_dir + "/" + file_name

    if os.path.exists(file_path):
        return

    print("Downloading " + file_name + " ... ")
    urllib.request.urlretrieve(url_base + file_name, file_path)
    print("Done")


def download_mnist():
    for v in key_file.values():
        _download(v)


def _load_label(file_name):
    file_path = dataset_dir + "/" + file_name

    print("Converting " + file_name + " to NumPy Array ...")
    with gzip.open(file_path, 'rb') as f:
        labels = np.frombuffer(f.read(), np.uint8, offset=8)
    print("Done")

    return labels


def _load_img(file_name):
    file_path = dataset_dir + "/" + file_name

    print("Converting " + file_name + " to NumPy Array ...")
    with gzip.open(file_path, 'rb') as f:
        data = np.frombuffer(f.read(), np.uint8, offset=16)
    data = data.reshape(-1, img_size)
    print("Done")

    return data


def _convert_numpy():
    dataset = {}
    dataset['train_img'] = _load_img(key_file['train_img'])
    dataset['train_label'] = _load_label(key_file['train_label'])
    dataset['test_img'] = _load_img(key_file['test_img'])
    dataset['test_label'] = _load_label(key_file['test_label'])

    return dataset


def init_mnist():
    download_mnist()
    dataset = _convert_numpy()
    print("Creating pickle file ...")
    with open(save_file, 'wb') as f:
        pickle.dump(dataset, f, -1)
    print("Done!")


def _change_one_hot_label(X):
    T = np.zeros((X.size, 10))
    for idx, row in enumerate(T):
        row[X[idx]] = 1

    return T


def load_mnist(normalize=True, flatten=True, one_hot_label=False):
    """读入MNIST数据集
    
    Parameters
    ----------
    normalize : 将图像的像素值正规化为0.0~1.0
    one_hot_label : 
        one_hot_label为True的情况下，标签作为one-hot数组返回
        one-hot数组是指[0,0,1,0,0,0,0,0,0,0]这样的数组
    flatten : 是否将图像展开为一维数组
    
    Returns
    -------
    (训练图像, 训练标签), (测试图像, 测试标签)
    """
    if not os.path.exists(save_file):
        init_mnist()

    with open(save_file, 'rb') as f:
        dataset = pickle.load(f)

    if normalize:
        for key in ('train_img', 'test_img'):
            dataset[key] = dataset[key].astype(np.float32)
            dataset[key] /= 255.0

    if one_hot_label:
        dataset['train_label'] = _change_one_hot_label(dataset['train_label'])
        dataset['test_label'] = _change_one_hot_label(dataset['test_label'])

    if not flatten:
        for key in ('train_img', 'test_img'):
            dataset[key] = dataset[key].reshape(-1, 1, 28, 28)

    return (dataset['train_img'], dataset['train_label']), (dataset['test_img'], dataset['test_label'])


if __name__ == '__main__':
    init_mnist()