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']
#1
a1 = np.dot(x, w1) + b1 #zhuyi x, w1de weizhi
z1 = sigmoid(a1)
#2
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))