neural_network
2016-09-18 22:44
405 查看
import numpy as np %matplotlib inline import matplotlib.pyplot as plt
N = 100 # number of points per class D = 2 # dimensionality K = 3 # number of classes X = np.zeros((N*K,D)) # data matrix (each row = single example) y = np.zeros(N*K, dtype='uint8') # class labels for j in range(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 # lets visualize the data: plt.scatter(X[:, 0], X[:, 1], c=y, s=40, cmap=plt.cm.Spectral)
<matplotlib.collections.PathCollection at 0x7febca3ea748>
#construct a two-layer neural_network # initialize parameters randomly h = 200 # size of hidden layer W = 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)) # some hyperparameters step_size = 1e-0 reg = 1e-3 # regularization strength # gradient descent loop num_examples = X.shape[0] for i in range(10000): # evaluate class scores, [N x K] hidden_layer = np.maximum(0, np.dot(X, W) + b) # note, ReLU activation 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
iteration 0: loss 1.098739 iteration 1000: loss 0.298098 iteration 2000: loss 0.264378 iteration 3000: loss 0.250640 iteration 4000: loss 0.249233 iteration 5000: loss 0.248823 iteration 6000: loss 0.248609 iteration 7000: loss 0.248480 iteration 8000: loss 0.248377 iteration 9000: loss 0.248280
# evaluate training set accuracy hidden_layer = np.maximum(0, np.dot(X, W) + b) scores = np.dot(hidden_layer, W2) + b2 predicted_class = np.argmax(scores, axis=1) print ('training accuracy: %.2f' % (np.mean(predicted_class == y)))
training accuracy: 0.99
predicted_class
array([2, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2])
相关文章推荐
- final,fianlly,fianlize的区别?
- gRPC使用的分析
- iOS 面试常见问题最全梳理(转)
- 手机网页版知乎内容隐藏效果的实现
- CentOS 7设置ssh服务自动启动
- SCPPO(十九):项目中SQL语句的一些应用总结
- DOM中的兄弟节点
- Java 版本的单项链表插入
- softmax_linear_classifier
- C++与多线程的线程安全
- 计算三角形面积的页面
- 欢迎使用CSDN-markdown编辑器
- 《信息安全系统设计基础》第1周学习总结
- Activiti学习文档(三)之画流程图并部署流程
- String.trim()
- 自制linux系统——打造属于自己的linux系统
- Android之进程通讯——广播
- Java编程题目-11:数组的交集
- 对onreadystatechange的理解
- hdu 2200 AC难题 数学排列组合