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()