Python: Neural Networks
来源:互联网 发布:java培训课程内容 编辑:程序博客网 时间:2024/06/13 02:23
这是用Python实现的Neural Networks, 基于Python 2.7.9, numpy, matplotlib。
代码来源于斯坦福大学的课程: http://cs231n.github.io/neural-networks-case-study/
基本是照搬过来,通过这个程序有助于了解python语法,以及Neural Networks 的原理。
import numpy as npimport matplotlib.pyplot as pltN = 200 # number of points per classD = 2 # dimensionalityK = 3 # number of classesX = np.zeros((N*K,D)) # data matrix (each row = single example)y = np.zeros(N*K, dtype='uint8') # class labelsfor j in xrange(K): ix = range(N*j,N*(j+1)) r = np.linspace(0.0,1,N) # radius t = np.linspace(j*4,(j+1)*4,N) + np.random.randn(N)*0.2 # theta X[ix] = np.c_[r*np.sin(t), r*np.cos(t)] y[ix] = j# print y# lets visualize the data:plt.scatter(X[:,0], X[:,1], s=40, c=y, alpha=0.5)plt.show()# Train a Linear Classifier# initialize parameters randomlyh = 20 # size of hidden layerW = 0.01 * np.random.randn(D,h)b = np.zeros((1,h))W2 = 0.01 * np.random.randn(h,K)b2 = np.zeros((1,K))# define some hyperparametersstep_size = 1e-0reg = 1e-3 # regularization strength# gradient descent loopnum_examples = X.shape[0]for i in xrange(1): # evaluate class scores, [N x K] hidden_layer = np.maximum(0, np.dot(X, W) + b) # note, ReLU activation # print np.size(hidden_layer,1) scores = np.dot(hidden_layer, W2) + b2 # compute the class probabilities exp_scores = np.exp(scores) probs = exp_scores / np.sum(exp_scores, axis=1, keepdims=True) # [N x K] # compute the loss: average cross-entropy loss and regularization corect_logprobs = -np.log(probs[range(num_examples),y]) data_loss = np.sum(corect_logprobs)/num_examples reg_loss = 0.5*reg*np.sum(W*W) + 0.5*reg*np.sum(W2*W2) loss = data_loss + reg_loss if i % 1000 == 0: print "iteration %d: loss %f" % (i, loss) # compute the gradient on scores dscores = probs dscores[range(num_examples),y] -= 1 dscores /= num_examples # backpropate the gradient to the parameters # first backprop into parameters W2 and b2 dW2 = np.dot(hidden_layer.T, dscores) db2 = np.sum(dscores, axis=0, keepdims=True) # next backprop into hidden layer dhidden = np.dot(dscores, W2.T) # backprop the ReLU non-linearity dhidden[hidden_layer <= 0] = 0 # finally into W,b dW = np.dot(X.T, dhidden) db = np.sum(dhidden, axis=0, keepdims=True) # add regularization gradient contribution dW2 += reg * W2 dW += reg * W # perform a parameter update W += -step_size * dW b += -step_size * db W2 += -step_size * dW2 b2 += -step_size * db2 # evaluate training set accuracyhidden_layer = np.maximum(0, np.dot(X, W) + b)scores = np.dot(hidden_layer, W2) + b2predicted_class = np.argmax(scores, axis=1)print 'training accuracy: %.2f' % (np.mean(predicted_class == y))
随机生成的数据
运行结果
0 0
- Python: Neural Networks
- Neural networks
- Neural Networks
- neural networks
- Neural Networks
- Neural Networks
- Neural Networks
- Neural Networks
- Neural Networks
- Neural Networks
- Using FANN and its Python bindings to construct neural networks
- neural networks deep learning Python Basics with numpy (optional) Homework
- Neural Networks网站
- Deep learning-------------Neural networks
- Neural Networks code
- Back-Propagation Neural Networks
- Convolutional Neural Networks
- 09: Neural Networks - Learning
- #define _syscall0(type,name) 详解
- 强类型语言JAVA与弱类型语言JS的小小认识
- SELinux安全上下文的认识
- Retrofit 2.0: 最好的Android HTTP客户端库的一次重大改变
- C语言结构体的初始化
- Python: Neural Networks
- iOS动画《第一篇》
- xampp集成环境自定义404页面失败解决办法
- 工作笔记 11
- [光速与物理]光的立方体效应
- Matlab拟合工具箱的几个误差参数说明
- sigar进行JAVA后台系统资源监控错误
- var s=+newDate();
- Maven主仓库中找不到包的解决办法(如org.restlet.jee not found)