Smallactive

import torchimport torch.nn as nnfrom torch.autograd import Variableimport numpy as npimport matplotlib.pyplot as plt# 超参数TIME_STEP = 10 # rnn time step INPUT_SIZE = 1 # rnn input sizeLR ...

视频教程：http://study.163.com/course/courseMain.htm?courseId=1004697005学习资料：https://zhuanlan.zhihu.com/p/21930884

import torchimport torch.nn.functional as fimport matplotlib.pyplot as pltfrom torch.autograd import Variable# 建造数据集x = torch.unsqueeze(torch.linspace(-1, 1, 100), dim=1)y = pow(x, 2) + 0.2*to...

import torchimport torch.nn.functional as ffrom torch.autograd import Variableimport matplotlib.pyplot as plt# 建造数据集data = torch.ones((100, 2))x0 = torch.normal(2*data, 1)y0 = torch.zeros(10...

传统法搭建神经网络：import torchimport torch.nn.functional as f# 传统法搭建神经网络模型class Net(torch.nn.Module): def __init__(self, n_feature, n_hidden, n_output): super(Net, self).__init__() ...

将神经网络训练好之后，如何保存它呢，保存它之后有如何提取它呢？如下图所示，net1是训练好的神经网络，有两种方式保存它：1.保存整个训练好的神经网络，2.保存神经网络的最终参数net2是根据第1种方式保存的。net2是根据第2种方式保存的源代码：# 引入模块import torchimport torch.nn.functional as ffrom torch.aut...

import torchimport torch.utils.data as Data# 虚构要训练的数据x = torch.linspace(11, 20, 10) # 在[11, 20]里取出10个间隔相等的数 (torch tensor)y = torch.linspace(20, 11, 10)BATCH_SIZE = 5 # 每批需要训练的数据个数# 把te...

 import torchimport torch.utils.data as Dataimport torch.nn.functional as Ffrom torch.autograd import Variableimport matplotlib.pyplot as plt# 构造假数据x = torch.unsqueeze(torch.linspace(-1, 1,...

import torchimport torch.nn as nnimport torch.utils.data as Dataimport torchvision # 视觉图片数据库from torch.autograd import Variableimport matplotlib.pyplot as plt# 超参数EPOCH = 1 # 为节省时间，只训练把数据训...

import torchimport torch.nn as nnimport torchvision.transforms as transformsfrom torch.autograd import Variableimport matplotlib.pyplot as pltimport torchvision.datasets as dsets# 超参数EPOCH =...