weixin_43963453的博客

import torch from torchvision import datasets from torchvision import transforms from torch.utils.data import DataLoader import torch.nn.functional as F import torch.optim as optim batch_size= 64 transoform =transforms.Compose([ transforms.ToTensor(),

import torch import numpy as np import matplotlib.pyplot as plt from torch.utils.data import Dataset # Dataset是个抽象类。继承它的类必须实现三个函数：init,getitem,len from torch.utils.data import DataLoader # DataLoader是用来处理一下原始数据的。Dataset只是用来存储数据的。 class MyModel(torch.nn.

import torch import numpy as np import matplotlib.pyplot as plt xy = np.loadtxt("diabetes.csv.gz", dtype=np.float32, delimiter=",") x = torch.from_numpy(xy[:, :-1]) y = torch.from_numpy(xy[:, [-1]]) # 这里[-1]是为了返回nx1的矩阵，如果只是一个-1的话，是没有维度的 class MyModel(tor

import torch import numpy as np import matplotlib.pyplot as plt x_data=torch.Tensor([[1.], [2.], [3.]]) y_data=torch.Tensor([[0.], [0.], [1.]]) class LogisticReg(torch.nn.Module): def __init__(self): super(LogisticReg,self).__init__()

import torch x_data=torch.Tensor([[1.], [2.], [3.]]) y_data=torch.Tensor([[2.], [4.], [6.]]) class MyModule(torch.nn.Module): def __init__(self): super(MyModule,self).__init__() self.linear=torch.nn.Linear(1,1) def forward(self,x)

import torch x_data=[1.0,2.0,3.0] y_data=[2.0,4.0,6.0] w=torch.Tensor([1.0]) w.requires_grad=True lr = 0.01 def forward(x): return x * w def loss(x,y): y_pred=forward(x) return (y_pred-y)**2 for epoch in range(100): for x,y in zip(x_da

import numpy as np import matplotlib.pyplot as plt #data x_data=[1.0, 2.0, 3.0] y_data=[2.0, 4.0, 6.0] #model def forward(x): return x * w #loss def loss(xs, ys): loss_val=0 for x,y in zip(xs,ys): y_pred=forward(x) loss_val+=

import numpy as np import matplotlib.pyplot as plt #data x_data=[1.0, 2.0, 3.0] y_data=[2.0, 4.0, 6.0] #model def forward(x): return x * w #loss def loss(x, y): return (y-forward(x))**2 w_list=[] mse_list=[] grad_list=[] for w in np.arange(0.0,