MNIST手写数字

Question

我尝试用python编写一个能够识别手写数字的脚本，使用的数据集是：http://deeplearning.net/data/mnist/mnist.pkl.gz。

有关这个问题和我正在尝试实现的算法的更多信息，可以在以下链接中找到：http://neuralnetworksanddeeplearning.com/chap1.html

我已经为每个数字实现了一个使用感知器的分类算法。

import cPickle, gzip
import numpy as np

f = gzip.open('mnist.pkl.gz', 'rb')
train_set, valid_set, test_set = cPickle.load(f)
f.close()

def activation(x):
    if x > 0:
        return 1
    return 0

bias = 0.5
learningRate = 0.01

images = train_set[0]
targets = train_set[1]

weights = np.random.uniform(0,1,(10,784))
for nr in range(0,10):
    for i in range(0,49999):
        x = images[i]
        t = targets[i]
        z = np.dot(weights[nr],x) + bias
        output = activation(z)
        weights[nr] = weights[nr] + (t - output) * x * learningRate
        bias = bias + (t - output) * learningRate

images = test_set[0]
targets = test_set[1]

OK = 0

for i in range range(0, 10000):
    vec = []
    for j in range(0,10):
        vec.append(np.dot(weights[j],images[i]))
    if np.argmax(vec) == targets[i]:
        OK = OK + 1

print("The network recognized " + str(OK) +'/'+ "10000")

我通常识别10%的数字，这意味着我的算法什么都不做，与随机算法相同。

尽管我知道这个问题很流行，而且我可以很容易地在网上找到另一个解决方案，但我仍然要求您帮助我识别代码中的错误。

也许我错误地初始化了learningRate，bias和weights的值。

Answer 1

多亏了@Kevinj22 22和其他人，我终于解决了这个问题。

import cPickle, gzip
import numpy as np

f = gzip.open('mnist.pkl.gz', 'rb')
train_set, valid_set, test_set = cPickle.load(f)
f.close()

def activation(x):
    if x > 0:
        return 1
    return 0

learningRate = 0.01

images = train_set[0]
targets = train_set[1]

weights = np.random.uniform(0,1,(10,784))

for nr in range(0,10):
    for i in range(0,50000):
        x = images[i]
        t = targets[i]
        z = np.dot(weights[nr],x)
        output = activation(z)
        if nr == t:
            target = 1
        else:
            target = 0
        adjust = np.multiply((target - output) * learningRate, x)
        weights[nr] = np.add(weights[nr], adjust)

images = test_set[0]
targets = test_set[1]

OK = 0

for i in range(0, 10000):
    vec = []
    for j in range(0,10):
        vec.append(np.dot(weights[j],images[i]))
    if np.argmax(vec) == targets[i]:
        OK = OK + 1

print("The network recognized " + str(OK) +'/'+ "10000")

这是我更新的代码。我在第一次尝试时没有引入损失计算。我也摆脱了偏见，因为我发现它在我的实现中没有用处。

我将这段代码运行了10次，平均准确率为88%