qq_42738654的博客

1.画图import torchimport torch.utils.data as Dataimport torch.nn.functional as Fimport matplotlib.pyplot as pltLR = 0.01BATCH_SIZE = 32EPOCH = 12x=torch.unsqueeze(torch.linspace(-1,1,1000),di...

1.保存网络import torchimport torch.nn.functional as Fimport matplotlib.pyplot as pltx=torch.unsqueeze(torch.linspace(-1,1,100),dim=1)# x data (tensor), shape=(100, 1)y=x.pow(2)+0.2*torch.rand(x.size(...

1.画图和第五课的画图代码一致，此处不多讲import torchimport torch.nn.functional as Fimport matplotlib.pyplot as plt#method 1n_data=torch.ones(100,2)x0=torch.normal(n_data*2,1)y0=torch.zeros(100)x1 = torch.norm...

1.画出散点图import torchimport torch.nn.functional as Fimport matplotlib.pyplot as pltn_data=torch.ones(100,2) #类似于np.ones()x0=torch.normal(n_data*2,1)y0=torch.zeros(100)x1 = torch.norma...

1.构造出散点图import torchimport numpy as npimport torch.nn.functional as Fimport matplotlib.pyplot as plt#x=torch.unsqueeze(torch.linspace(-1,1,100),dim=1)## x data (tensor), shape=(100, 1),这里的是把一维变成...

1.各种激励函数首先介绍一下import torch.nn.functional as F，激励函数在里面找，后几章会有import torch.nn as nn,这个里面也存在的激励函数，那么他们有什么区别呢？F.conv2d()类似于python的一个函数,而nn.Conv2d是一个类，他是通过而nn.Conv2d的forward()函数实现是用F.conv2d()实现的import t...

1.tensor转变为Variable变量首先需要解释一个库from torch.autograd import Variable，提到这个库就必须要提到Variable，简而言之，Variable就是一个tensor的外衣，里面有三个属性.data, .grad和.grad_fn（老版的是.creator），其中data属性存储着tensor数据，grad属性存储关于该变量的导数（当然只有BP...

1. torch类型numpy的互相转换import numpy as npimport tensorflow as tfimport torchnp_data = np.arange(6).reshape((2, 3)) #（2,3）torch_data = torch.from_numpy(np_data) #转换成tensortensor2array = torch_d...

１.构造数据集import torchfrom torch import nnfrom torch.nn import initimport torch.utils.data as Dataimport matplotlib.pyplot as pltimport numpy as npN_SAMPLES = 2000BATCH_SIZE = 64EPOCH = 12LR =...

１．构造数据集import matplotlib.pyplot as pltN_SAMPLES = 20N_HIDDEN = 300x=torch.unsqueeze(torch.linspace(-1,1,N_SAMPLES),1)y=x+0.3*torch.normal(torch.zeros(N_SAMPLES,1),torch.ones(N_SAMPLES,1))# tes...

１.画出大师作品（构造目标）import torchimport torch.nn as nnimport numpy as npimport matplotlib.pyplot as plttorch.manual_seed(1) # 设置种子np.random.seed(1)BATCH_SIZE = 64LR_G = 0.0001 # （生成网络）...

import torchimport torch.nn as nnimport torch.utils.data as Dataimport torchvisionimport matplotlib.pyplot as pltfrom mpl_toolkits.mplot3d import Axes3Dfrom matplotlib import cmimport numpy as ...

1.构造数据import torchfrom torch import nnimport numpy as npimport matplotlib.pyplot as plt# Hyper ParametersTIME_STEP = 10 # rnn time stepINPUT_SIZE = 1 # rnn input sizeLR = 0.02 ...

1.下载数据集和CNN数据集一致，不多叙述import torchfrom torch import nnimport torchvision.datasets as dsetsimport torchvision.transforms as transformsimport matplotlib.pyplot as plt# torch.manual_seed(1) #设置...

import torchvision用来生成图片,视频数据集,和一些流行的模型类和预训练模型。1.生成数据集import torchimport torch.nn as nnimport torch.utils.data as Dataimport torchvision # 数据库模块import matplotlib.pyplot as plttorch.manual...

首先介绍一下import torch.utils.data as Data，这在训练过程中基本都会用到。该接口大多用来读取数据和把数据封装成Tensor，之后的DataLoader用来做mini—batch训练。import torchimport torch.utils.data as DataBATCH_SIZE=5x=torch.linspace(1,10,10)y=torch...