network.py
来源:互联网 发布:数控立车编程操作入门 编辑:程序博客网 时间:2024/06/08 10:38
import random# Third-party librariesimport numpy as npclass Network(object): def __init__(self, sizes): self.num_layers = len(sizes) self.sizes = sizes self.biases = [np.random.randn(y, 1) for y in sizes[1:]] self.weights = [np.random.randn(y, x) for x, y in zip(sizes[:-1], sizes[1:])] def feedforward(self, a): """Return the output of the network if ``a`` is input.""" for b, w in zip(self.biases, self.weights): a = sigmoid(np.dot(w, a)+b) return a def SGD(self, training_data, epochs, mini_batch_size, eta, test_data=None): if test_data: test_data = list(test_data) n_test = len(test_data) training_data = list(training_data) n = len(training_data) for j in range(epochs): random.shuffle(training_data) mini_batches = [ training_data[k:k+mini_batch_size] for k in range(0, n, mini_batch_size)] for mini_batch in mini_batches: self.update_mini_batch(mini_batch, eta) if test_data: print ("Epoch {0}: {1} / {2}".format( j, self.evaluate(test_data), n_test)) else: print ("Epoch {0} complete".format(j)) def update_mini_batch(self, mini_batch, eta): """Update the network's weights and biases by applying gradient descent using backpropagation to a single mini batch. The ``mini_batch`` is a list of tuples ``(x, y)``, and ``eta`` is the learning rate.""" nabla_b = [np.zeros(b.shape) for b in self.biases] nabla_w = [np.zeros(w.shape) for w in self.weights] for x, y in mini_batch: delta_nabla_b, delta_nabla_w = self.backprop(x, y) nabla_b = [nb+dnb for nb, dnb in zip(nabla_b, delta_nabla_b)] nabla_w = [nw+dnw for nw, dnw in zip(nabla_w, delta_nabla_w)] self.weights = [w-(eta/len(mini_batch))*nw for w, nw in zip(self.weights, nabla_w)] self.biases = [b-(eta/len(mini_batch))*nb for b, nb in zip(self.biases, nabla_b)] def backprop(self, x, y): """Return a tuple ``(nabla_b, nabla_w)`` representing the gradient for the cost function C_x. ``nabla_b`` and ``nabla_w`` are layer-by-layer lists of numpy arrays, similar to ``self.biases`` and ``self.weights``.""" nabla_b = [np.zeros(b.shape) for b in self.biases] nabla_w = [np.zeros(w.shape) for w in self.weights] # feedforward activation = x activations = [x] # list to store all the activations, layer by layer zs = [] # list to store all the z vectors, layer by layer for b, w in zip(self.biases, self.weights): z = np.dot(w, activation)+b zs.append(z) activation = sigmoid(z) activations.append(activation) # backward pass delta = self.cost_derivative(activations[-1], y) * sigmoid_prime(zs[-1]) nabla_b[-1] = delta nabla_w[-1] = np.dot(delta, activations[-2].transpose()) # Note that the variable l in the loop below is used a little # differently to the notation in Chapter 2 of the book. Here, # l = 1 means the last layer of neurons, l = 2 is the # second-last layer, and so on. It's a renumbering of the # scheme in the book, used here to take advantage of the fact # that Python can use negative indices in lists. for l in range(2, self.num_layers): z = zs[-l] sp = sigmoid_prime(z) delta = np.dot(self.weights[-l+1].transpose(), delta) * sp nabla_b[-l] = delta nabla_w[-l] = np.dot(delta, activations[-l-1].transpose()) return nabla_b, nabla_w def evaluate(self, test_data): """Return the number of test inputs for which the neural network outputs the correct result. Note that the neural network's output is assumed to be the index of whichever neuron in the final layer has the highest activation.""" test_results = [(np.argmax(self.feedforward(x)), y) for (x, y) in test_data] return sum(int(x == y) for (x, y) in test_results) def cost_derivative(self, output_activations, y): """Return the vector of partial derivatives \partial C_x / \partial a for the output activations.""" return (output_activations-y)#### Miscellaneous functionsdef sigmoid(z): """The sigmoid function.""" return 1.0/(1.0+np.exp(-z))def sigmoid_prime(z): """Derivative of the sigmoid function.""" return sigmoid(z)*(1-sigmoid(z))
0 0
- network.py
- Python Intro - network.py migration to Python3
- neural-networks-and-deep-learning network.py
- py
- py
- py
- py
- py
- py
- py
- Py
- [network]
- NETWORK
- Network
- network
- network
- Network
- NETWORK
- 《道德经》第十二章
- Java架构师之路高级进阶教程
- mysql导库遇到的问题
- CentOS7单用户模式下修改root用户密码
- CheckStyle使用中遇到的问题
- network.py
- 文章标题
- CPU和GPU的设计区别
- JAVA中json转换
- JavaScript跨浏览器事件对象EventUtil(IE中event对象和方法DOM中都有,此处提供两者映射方法)
- Android代码混淆学习
- JS获取地址栏URL参数
- [NODE之10]os模块
- 奇特的锡纸海鲜小吃:吃到嗨都不会发胖的辣卤海鲜!值得开一家哦!