- 博客(16)
- 收藏
- 关注
RSS订阅转载 sklearn---onehotcode
非常好的文章https://www.cnblogs.com/zhoukui/p/9159909.html
2019-08-16 22:45:05
185
原创 jieba
1.# encoding=utf-8import jiebaimport jieba.posseg as psegprint("\njieba分词全模式：")seg_list = jieba.cut("我来到北京清华大学", cut_all=True)print("Full Mode: " + "/、 ".join(seg_list)) # 全模式strings="是广泛...
2019-08-15 01:29:19
160
原创 pytorch-7交叉商1
定义：def cross_entropy(input, target, weight=None, size_average=None, ignore_index=-100, reduce=None, reduction='mean'): # type: (Tensor, Tensor, Optional[Tensor], Optional[boo...
2019-08-01 21:16:28
188
原创 pytorch-6线性优化
1.可视化，meshgrid合并x，ydef fun(x): return (x[0]**2+x[1]-11)**2+(x[0]+x[1]**2-7)**2x=np.arange(-6,6,0.1)y=np.arange(-6,6,0.1)X,Y=np.meshgrid(x,y)print(X.shape)print(Y.shape)Z=fun([X,Y])fig=p...
2019-08-01 20:53:02
148
原创 pytorch5求导
import torchfrom torch.nn import functionalx=torch.ones(1,requires_grad=True)print(x)w=torch.full([1],6,requires_grad=True)mse=functional.mse_loss(x,x*w)print(mse)#(1-6)**2print(torch.autograd...
2019-08-01 00:32:03
75
原创 pytorch基础学习5
1.whereimport torchcond=torch.tensor([[0.6,0.4],[0.7,0.3]])a=torch.tensor([[0.,0.],[0.,0.]])b=torch.tensor([[1.,1.],[1.,1.]])c=torch.where(cond>0.5,a,b)print(a)print(b)print(c)结果：tensor...
2019-07-31 22:15:26
89
原创 pytourch基础学习4
1.matmul/@/mm（二维）矩阵相乘import torcha=torch.randn(4,2,3,8)b=torch.randn(4,2,8,8)print(torch.matmul(a,b).shape)结果：torch.Size([4, 2, 3, 8])2.pow/**import torcha=torch.full([2,2],9)print(a)b...
2019-07-31 21:21:00
276
原创 pytourch基础学习3
1.合并import torcha=torch.randn(5,2,3,8)b=torch.randn(4,2,3,8)print(torch.cat([a,b],dim=0).shape)结果：torch.Size([9, 2, 3, 8])2.stack增加维度import torcha=torch.randn(4,2,3,8)b=torch.randn(4,2,...
2019-07-31 20:31:07
180
原创 pytorch基础学习2
1.切片import torchb=torch.tensor([[[1, 2, 3,4]]])print(b)a=b[:,:,0:4:2].shapeprint(a)print(b[:,:,0:4:2])print(b)结果：tensor([[[1, 2, 3, 4]]])torch.Size([1, 1, 2])tensor([[[1, 3]]])tensor([[[...
2019-07-30 14:22:51
70
原创 pytorch基础学习1
1.从numpy导入import torchimport numpy as npa=np.array([2,2.3])b=torch.from_numpy(a)print(a)print(b)a=np.ones([2,3])b=torch.from_numpy(a)print(a)print(b)结果：[2. 2.3]tensor([2.0000, 2.3000],...
2019-07-30 13:00:38
72
原创 sklearn
from sklearn import datasetsfrom sklearn.linear_model import LinearRegressionimport numpy as npimport matplotlib.pyplot as pltdata=datasets.load_boston()data_x=data.datadata_y=data.targetmodel...
2019-07-07 16:25:27
60
转载 逻辑回归，凸函数
原文链接：https://www.jianshu.com/p/894bda167422https://tech.meituan.com/2015/05/08/intro-to-logistic-regression.htmlhttps://blog.csdn.net/Julialove102123/article/details/78405261写文章注册登录首页 下载App...
2019-07-07 16:08:14
1575
转载 线性回归3
coding=utf-8线性回归-单特征梯度下降练习from numpy import *import matplotlib.pyplot as pltfrom matplotlib import animationimport numpy as np【1】特征缩放 X:=[X-mean(X)]/std(X) || X:=[X-min(X)]/max(X)-min(X) ;def f...
2019-07-06 18:03:46
97
原创 线性回归2
1.特征放缩对于多特征的线性回归，为了平衡各特征之间的权重，采用特征放缩eg：size（0-2000）1000-平均值 bedroom（1-5）2-平均值2.梯度下降法是否运行正确画出代价函数和步数的关系图3.学习率0.001，0.003，0.01，0.03，0.1，........
2019-07-06 17:57:08
83
空空如也
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人