![](https://img-blog.csdnimg.cn/20201014180756923.png?x-oss-process=image/resize,m_fixed,h_64,w_64)
跟着XiaoChao学AI
XiaoChao_AI
这个作者很懒,什么都没留下…
展开
-
人工智能NLP自然语言之基础篇文本分类pytorch-transformers实现BERT文本分类bert
一、数据集介绍中文文本分类数据集数据来源:今日头条客户端数据格式:6554695793956094477_!_110_!_news_military_!_「欧洲第一陆军」法兰西帝国的欧陆霸权_!_查理八世,布列塔尼,卡佩王朝,佛兰德斯,法国6554855520291783175_!_110_!_news_military_!_以色列为巷战而研发的重型装甲运兵车,美军也租一辆进行作战测试_!_装甲运兵车,重型步兵战车,步兵战车,以色列,雌虎,M113,T-55652515515675600538原创 2021-12-07 11:08:36 · 1948 阅读 · 0 评论 -
自然语言之基础篇文本分类pytorch-transformers实现BERT文本分类bert
一、数据集介绍中文文本分类数据集数据来源:今日头条客户端数据格式:6554695793956094477_!_110_!_news_military_!_「欧洲第一陆军」法兰西帝国的欧陆霸权_!_查理八世,布列塔尼,卡佩王朝,佛兰德斯,法国6554855520291783175_!_110_!_news_military_!_以色列为巷战而研发的重型装甲运兵车,美军也租一辆进行作战测试_!_装甲运兵车,重型步兵战车,步兵战车,以色列,雌虎,M113,T-55652515515675600538原创 2021-12-07 10:55:31 · 1116 阅读 · 0 评论 -
pytorch之CNN网络
链接:https://pan.baidu.com/s/1M8wmDbcBmhaui9V20Lttaw 提取码:qhi9。原创 2021-06-21 10:56:41 · 252 阅读 · 0 评论 -
tensorflow之用LSTM实现hihell->ihello
LSTM实现hihell->ihello//hihell->ihelloimport tensorflow as tfimport numpy as np#datachar_x = 'hihell'char_y = 'ihello'char = char_x+char_y#Eliminate duplicate valueschar = list(set(char))#word to idchar_set = {w:i for i,w in enumerate(char)原创 2021-06-20 19:38:13 · 170 阅读 · 0 评论 -
机器学习之PCA(降维算法)
PCA降维// PCAimport numpy as npimport matplotlib.pyplot as pltimport scipy.iofrom scipy.linalg import svdimage = plt.imread('leena.jpg')print("image: ", image.shape)plt.figure()plt.imshow(image)plt.show()X = imageh, w, ch = X.shapeK = 90Xre原创 2021-06-19 09:30:47 · 166 阅读 · 0 评论 -
机器学习之聚类(clustering)
clustering// 机器学习之聚类import numpy as npimport matplotlib.pyplot as pltimport scipy.io as siodata = sio.loadmat('ex7data2.mat')X = data['X']m = len(X)center = np.array([[3, 3], [6, 2], [8, 5]]) # 可随机数据点作为质心# center = np.array([[2, 0], [0, 1], [0,原创 2021-06-19 09:28:57 · 258 阅读 · 0 评论 -
机器学习之支持向量机
支持向量机// 机器学习支持向量机import numpy as npfrom sklearn import svmimport matplotlib.pyplot as plt# 1. 完成数据集的加载和初始化data = np.loadtxt('bread.txt', delimiter=',')X, y = np.hsplit(data, [-1, ])m, n = X.shape# 2. 将数据集洗牌,合理分割成训练集和测试集p = np.random.permutatio原创 2021-06-19 09:26:04 · 131 阅读 · 0 评论 -
机器学习之独热隐藏层神经网络
隐藏层神经网络// 神经网络import numpy as npimport matplotlib.pyplot as pltimport scipy.io as siodata = sio.loadmat('ex3data1.mat')x = data['X']raw_y = data['y']X = np.insert(x, 0, 1, axis=1)m, n = X.shapedef one_hot_encode(y): result = [] for i原创 2021-06-19 09:23:32 · 187 阅读 · 0 评论 -
机器学习之二分类画出决策边界
二分类画出决策边界// 二分类决策边界import numpy as npimport matplotlib.pyplot as pltdata = np.loadtxt('ex2data2.txt', delimiter=',')x, y = np.hsplit(data, [-1, ])X = np.insert(x, 0, 1, axis=1)def Map(x1, x2): degrees = 6 out = np.ones((x1.shape[0], 1))原创 2021-06-19 09:20:38 · 1326 阅读 · 0 评论 -
机器学习之正则化实现
正则化实现//正则化import numpy as npimport matplotlib.pyplot as plt# 1. 完成数据集的读取data_s1 = np.loadtxt('s1.txt', delimiter=',')data_s2 = np.loadtxt('s2.txt', delimiter=',')# x_s1, y_s1 = data_s1[:, :-1], data_s1[:, -1:]# x_s2, y_s2 = data_s2[:, :-1], data原创 2021-06-19 09:18:19 · 279 阅读 · 0 评论 -
机器学习之多项式回归
多项式回归的实现// 多项式回归import numpy as npimport matplotlib.pyplot as pltnp.random.seed(0)x0 = np.random.random(50)y = 2 * x0 ** 3 + 1.2 * x0 ** 2 + 1.5def degreed(x0): degreed = 3 onex = np.c_[np.ones(len(x0))] for i in range(1, degreed+1):原创 2021-06-19 09:15:01 · 93 阅读 · 0 评论 -
机器学习之逻辑回归
逻辑回归机器学习之逻辑回归实现// An highlighted blockimport numpy as npimport matplotlib.pyplot as plt#前向传播def model(onex, theta): z = np.dot(onex, theta) h = 1 / (1 + np.exp(-z)) return h#损失函数def costFunc(m, h, y): J = (-1 / m) * np.sum(y * np.原创 2021-06-19 09:12:19 · 67 阅读 · 0 评论 -
机器学习之线性回归
线性回归1.单变量线性回归// 单变量线性回归import numpy as npimport matplotlib.pyplot as plt#读取数据加载数据data = np.loadtxt('ex1data1.txt', delimiter=',')x = data[:, :-1]y = data[:, -1:]X = np.insert(x, 0, 1, axis=1)#前向传播def model(theta, X): h = np.dot(X, theta)原创 2021-06-19 09:06:30 · 133 阅读 · 0 评论 -
tensorflow1.X实现线性回归+可视化处理
tensorflow1.X实现线性回归+可视化处理首先安装tensorflow方式一:pip install tensorflow-gpu==1.14.0 -i https://pypi.tuna.tsinghua.edu.cn/simple方式二:conda install tensorflow-gpu==1.14这里推荐使用pip的方式安装安装GPU版本需要配置CUDA,相关文章到我的另一篇博客:https://blog.csdn.net/qq_38008528/article/detail原创 2021-06-19 08:25:52 · 307 阅读 · 0 评论