import torch
from torch.autograd import Variable
import torch.nn.functional as F
import numpy as np
n_data = torch.ones(100,2) # 打印[100,2]矩阵的1
# 第一个数据集
x0 = torch.normal(2*n_data,1)
y0 = torch.zeros(100)
# 第二个数据集
x1 = torch.normal(-2*n_data,1)
y1 = torch.ones(100)
# 合并数据集 --> 合并 并改变格式
x = torch.cat((x0,x1),0).type(torch.FloatTensor) # 32位浮点数
y = torch.cat((y0,y1)).type(torch.LongTensor) # 64 位整型
tensor([[-1.8586, -2.7746],
[-2.8297, -2.1551],
[-2.4832, -2.2842],
[-1.9556, -1.9917],
[-2.5398, -2.1877],
[-2.6220, -2.5604]])
定义一个神经网络(用于分类)
class Net(torch.nn.Module):
def __init__(self,n_feature,n_hidden,n_output):
super(Net,self).__init__()
self.hidden = torch.nn.Linear(n_feature,n_hidden)
self.predict = torch.nn.Linear(n_hidden,n_output)
pass
def forward(self,x):
x = F.relu(self.hidden(x))
x =self.predict(x)
return x
分类的时候使用 CrossEntropyLoss() 概率误差比较好
net = Net(2,10,2)
print(net)
optimizer = torch.optim.SGD(net.parameters(),lr=0.1)
loss_func = torch.nn.CrossEntropyLoss() # 标签误差
Net(
(hidden): Linear(in_features=2, out_features=10, bias=True)
(predict): Linear(in_features=10, out_features=2, bias=True)
)
for i in range(100):
prediction = net(x)
loss = loss_func(prediction,y)
# 梯度归零
optimizer.zero_grad()
# 计算梯度
loss.backward()
# 更新结点
optimizer.step()
if i % 20 == 0:
print(loss)
tensor(0.5676, grad_fn=<NllLossBackward>)
tensor(0.0800, grad_fn=<NllLossBackward>)
tensor(0.0339, grad_fn=<NllLossBackward>)
tensor(0.0204, grad_fn=<NllLossBackward>)
tensor(0.0143, grad_fn=<NllLossBackward>)
如何预测
x1 = torch.FloatTensor([2,2])
x1 = Variable(x1)
# 这样可以是实现预测
np.argmax(net(x1).data.numpy)