自己动手实现一个网络模型 python

转自：https://www.jianshu.com/p/4b30e1dd2252

common_funcs.py

import numpy as np
import matplotlib.pyplot as plt

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

def softmax(a):
    exp_a = np.exp(a)
    sum_exp_a = np.sum(exp_a)
    y = exp_a / sum_exp_a
    return y

def cross_entroy_error(y, t):
    if y.ndim == 1:
        t = t.reshape(1, t.size)
        y = y.reshape(1, y.size)

    if t.size == y.size:
        t = t.argmax(axis=1)

    batch_size = y.shape[0]
    return -np.sum(np.log(y[np.arange(batch_size), t]+1e-7))/batch_size

def numerical_gradient(f, x):
    h = 1e-4
    grad = np.zeros_like(x)
    it = np.nditer(x,flags = ['multi_index'], op_flags = ['readwrite'])
    while not it.finished:
        idx = it.multi_index
        tmp_val = x[idx]
        x[idx] = float(tmp_val) + h
        fxh1 = f(x)

        x[idx] = tmp_val-h
        fxh2 = f(x)
        grad[idx] = (fxh1 - fxh2)/(2*h)

        x[idx] = tmp_val
        it.iternext()
    return grad

def function_2(x):
    return np.sum(x**2)

TeoLayerNet.py
import numpy as np
from common_funcs import sigmoid, softmax, cross_entroy_error,numerical_gradient
class TwoLayerNet:

    def __init__(self, input_size, hidden_size, output_size, weight_init_std = 0.01):
        self.params = {'w1':weight_init_std*np.random.randn(input_size,hidden_size),
                       'b1':np.zeros(hidden_size),
                       'w2':weight_init_std*np.random.randn(hidden_size,output_size),
                       'b2':np.zeros(output_size)}

    def predict(self,x):
        w1, w2 = self.params['w1'], self.params['w2']
        b1, b2 = self.params['b1'], self.params['b2']
        #
        a1 = np.dot(x, w1) + b1 #zhuyi x, w1de weizhi
        z1 = sigmoid(a1)
        #
        a2 = np.dot(z1, w2) + b2
        y = softmax(a2)
        return y

    def loss(self, x, t):
        y = self.predict(x)
        return cross_entroy_error(y, t)

    def accuracy(self, x, t):
        y = self.predict(x)
        y = np.argmax(y, axis=1)
        t = np.argmax(t, axis=1)

        accuracy = np.sum(y == t)/float(x.shap[0])
        return accuracy

    def gradient(self, x, t):
        loss_w = lambda w: self.loss(x, t)

        grads = {}
        grads['w1'] = numerical_gradient(loss_w, self.params['w1'])
        grads['b1'] = numerical_gradient(loss_w, self.params['b1'])
        grads['w2'] = numerical_gradient(loss_w, self.params['w2'])
        grads['b2'] = numerical_gradient(loss_w, self.params['b2'])

        return grads

minist.py
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'])

main.py
import numpy as np
import matplotlib.pyplot as plt
from mnist import load_mnist
from TwoLayerNet import TwoLayerNet

(x_train, t_train),(x_test, t_test) = load_mnist(normalize = True, one_hot_label = True)

train_loss_list = []
train_acc_list = []
test_acc_list = []

iter_num = 10000
train_size = x_train.shape[0]
batch_size = 100
learning_rate = 0.1
iter_per_epoch = max(train_size / batch_size, 1)

net_work = TwoLayerNet(input_size=784, hidden_size=50, output_size=10)

for i in range(iter_num):
    batch_mask = np.random.choice(train_size, batch_size)
    x_batch = x_train[batch_mask]
    t_batch = t_train[batch_mask]

    grad = net_work.gradient(x_batch, t_batch)

    for key in ('w1', 'b1', 'w2', 'b2'):
        net_work.params[key] -= learning_rate*grad[key]

    if i % iter_per_epoch == 0:
        loss = net_work.loss(x_train, t_train)
        train_loss_list.append(loss)
        train_acc = net_work.accuracy(x_train, t_train)
        train_acc_list.append(train_acc)
        test_acc = net_work.accuracy(x_test, t_test)
        test_acc_list.append(test_acc)
        print('run... loss:{} train acc:{} test acc:{}'.format(loss, train_acc,test_acc))