1、 Python plt绘图

使用Python的绘图，制作训练的迭代次数与准确率、损失函数值的图像：

使用说明代码

---

使用说明

Introduction　简介：

我们在用MATLAB绘图时感觉很轻巧，那么在Python中，怎么使用plot呢？下面是一个简单的例子，使用linspace定义自变量的取值范围，文档中其说明为： np.linspace(start, stop, num, endpoint, retstep, dtype)， 我们只需要了解前面3个，小标开始的数字、结束的数字、数字数字个数。好，直接showcode

代码块

代码，例如：

import numpy as np import matplotlib.pyplot as plt from pylab import * mpl.rcParams['font.sans-serif']=['SimHei'] tra_accuracy=[0.12,0.23,0.31,0.34,0.43,0.51,0.55,0.66,0.68,0.74,0.8,0.9] test_acc = [0.4,0.5,0.6,0.7,0.8,0.9] a=np.linspace(0,100,2) print(a) #正确率绘图 fig1=plt.figure('fig1') plt.plot(np.linspace(0, 11, len(tra_accuracy)),tra_accuracy,'b-',label='训练的正确率') plt.plot(np.linspace(0, 10, len(test_acc)),test_acc,'k-.',label='测试的正确率') plt.title('训练、测试的正确率') plt.xlabel('迭代次数') plt.ylabel('准确率') plt.legend(loc='lower right') >>> plt.show(fig1)

2、绘制柱状图

# _*_coding:utf-8_*_ __author__ = 'Alex_XT' import numpy as np import matplotlib.pyplot as plt x=[0,1,2,3,4,5,6,7,8,9] y=[12,23,4,10,22,33,44,23,35,7] plt.bar(x,y,align='center',alpha=0.5) plt.xticks(x,x) plt.ylabel('count') plt.title('Distribution') plt.show()

3、画准确率图

# _*_coding:utf-8_*_ __author__ = 'Alex_XT' from pylab import * mpl.rcParams['font.sans-serif']=['SimHei']#导入中文 import numpy as np import matplotlib.pyplot as plt y=[1.0,0.982,0.97,0.95,0.92,0.620] y2=[0.989,0.967,0.43,0.44,0.48,0.3] plt.plot(np.linspace(40,50,6),y,'r-*',label='Swish') plt.plot(np.linspace(40,50,6),y2,'b-d',label='ReLu') plt.legend(loc='lower left') plt.ylabel('准确率') plt.xlabel('网络层数') plt.title('MNIST数据集中不同网络层数测试') plt.show()

4、等比数列的图，但xlabel却是等间距的

# _*_coding:utf-8_*_ __author__ = 'Alex_XT' from pylab import * mpl.rcParams['font.sans-serif']=['SimHei']#导入中文 import numpy as np import matplotlib.pyplot as plt x=np.linspace(1,5,5) xt=np.logspace(0,4,5,base=2)*128#等比 print(xt) y=[92.4,92.22,92.2091,91.8,91.45] y2=[92.0,91.90,92.01,91.402,91.302] plt.plot(x,y,'r-*',label='Swish') plt.plot(x,y2,'b-d',label='ReLu') plt.legend(loc='upper right') plt.xticks(x,xt) plt.ylabel('准确率') plt.xlabel('Batch Size') plt.title('MNIST数据集中不同BatchSize大小测试') plt.show()

5、画Logistic的Sigmoid函数图

# _*_coding:utf-8_*_ __author__ = 'Alex_XT' # Python imports import numpy as np # Matrix and vector computation package import matplotlib.pyplot as plt # Plotting library # Define the logistic function def logistic(z): return 1 / (1 + np.exp(-z)) # Plot the logistic function z = np.linspace(-6,6,100) plt.plot(z, logistic(z), 'b-') plt.xlabel('$z$', fontsize=15) plt.ylabel('$\sigma(z)$', fontsize=15) plt.title('logistic function') plt.grid() plt.show()

求导函数的图形：

# _*_coding:utf-8_*_ __author__ = 'Alex_XT' # Python imports import numpy as np # Matrix and vector computation package import matplotlib.pyplot as plt # Plotting library # Define the logistic function def logistic(z): return 1 / (1 + np.exp(-z)) # Define the logistic derivative function def logistic_derivative(z): return logistic(z) * (1 - logistic(z)) # Plot the derivative of the logistic function z = np.linspace(-6,6,100) plt.plot(z, logistic_derivative(z), 'r-') plt.xlabel('$z$', fontsize=15) plt.ylabel('$\\frac{\\partial \\sigma(z)}{\\partial z}$', fontsize=15) plt.title('derivative of the logistic function') plt.grid() plt.show()

6、画Softmax三维图

# _*_coding:utf-8_*_ __author__ = 'Alex_XT' import numpy as np # Matrix and vector computation package import matplotlib.pyplot as plt # Plotting library from matplotlib.colors import colorConverter, ListedColormap # some plotting functions from mpl_toolkits.mplot3d import Axes3D # 3D plots from matplotlib import cm # Colormaps # Allow matplotlib to plot inside this notebook # Define the softmax function def softmax(z): return np.exp(z) / np.sum(np.exp(z)) # Plot the softmax output for 2 dimensions for both classes # Plot the output in function of the weights # Define a vector of weights for which we want to plot the ooutput nb_of_zs = 200 zs = np.linspace(-10, 10, num=nb_of_zs) # input zs_1, zs_2 = np.meshgrid(zs, zs) # generate grid y = np.zeros((nb_of_zs, nb_of_zs, 2)) # initialize output # Fill the output matrix for each combination of input z's for i in range(nb_of_zs): for j in range(nb_of_zs): y[i,j,:] = softmax(np.asarray([zs_1[i,j], zs_2[i,j]])) # Plot the cost function surfaces for both classes fig = plt.figure() # Plot the cost function surface for t=1 ax = fig.gca(projection='3d') surf = ax.plot_surface(zs_1, zs_2, y[:,:,0], linewidth=0, cmap=cm.coolwarm) ax.view_init(elev=30, azim=70) cbar = fig.colorbar(surf) ax.set_xlabel('$z_1$', fontsize=15) ax.set_ylabel('$z_2$', fontsize=15) ax.set_zlabel('$y_1$', fontsize=15) ax.set_title ('$P(t=1|\mathbf{z})$') cbar.ax.set_ylabel('$P(t=1|\mathbf{z})$', fontsize=15) plt.grid() plt.show()

7、画ELU激活函数

# _*_coding:utf-8_*_ __author__ = 'Alex_XT' # Python imports import numpy as np # Matrix and vector computation package import matplotlib.pyplot as plt # Plotting library # Define the ELU function def ELU(z): new_z = [] for i in z: if i > 0: new_z.append(i) else: new_z.append(np.exp(i) - 1) return new_z # Plot the ELU function z = np.linspace(-10, 15, 100) plt.plot(z, ELU(z), 'r-') plt.xlabel('$x$', fontsize=15) plt.ylabel('$f(x)$', fontsize=15) plt.title('ELU') plt.grid() plt.show()