PyTorch简单的神经网络-- 莫烦

PyTorch简单的神经网络

import torch
import torch.nn.functional as F
import matplotlib.pyplot as plt
%matplotlib inline

torch.manual_seed(1)    # reproducible
x = 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())                 # noisy y data (tensor), shape=(100, 1)
 
plt.scatter(x.data.numpy(), y.data.numpy())
plt.show()

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)   # hidden layer
        self.predict = torch.nn.Linear(n_hidden, n_output)   # output layer

    def forward(self, x):
        x = F.relu(self.hidden(x))      # activation function for hidden layer
        x = self.predict(x)             # linear output
        return x
        
net = Net(n_feature=1, n_hidden=10, n_output=1)     # define the network
print(net)  # net architecture
print(net.parameters())

optimizer = torch.optim.SGD(net.parameters(), lr=0.2)
loss_func = torch.nn.MSELoss()  # this is for regression mean squared loss 回归问题的均方差Loss

plt.ion()   # something about plotting       matplotlib实时打印
for t in range(100):
    prediction = net(x)     # input x and predict based on x

    loss = loss_func(prediction, y)     # must be (1. nn output, 2. target)

    optimizer.zero_grad()   # clear gradients for next train  # 每次梯度计算完成后都会保留在optimizer中，要清零
    loss.backward()         # backpropagation, compute gradients
    optimizer.step()        # apply gradients

    if t % 10 == 0:
        # plot and show learning process
        plt.cla()
        plt.scatter(x.data.numpy(), y.data.numpy())
        plt.plot(x.data.numpy(), prediction.data.numpy(), 'r-', lw=5)
        plt.text(0.5, 0, 'Loss=%.4f' % loss.data.numpy(), fontdict={'size': 20, 'color':  'red'})
        plt.show()
        plt.pause(0.1)

plt.ioff()

import torch
from torch.autograd import Variable
import torch.nn.functional as F
import matplotlib.pyplot as plt
%matplotlib inline
torch.manual_seed(1)    # reproducible

# make fake data
n_data = torch.ones(100, 2)
x0 = torch.normal(2*n_data, 1)      # class0 x data (tensor), shape=(100, 2) 第一类的横纵坐标
y0 = torch.zeros(100)               # class0 y data (tensor), shape=(100, 1) 第一类的标签全是0
x1 = torch.normal(-2*n_data, 1)     # class1 x data (tensor), shape=(100, 2) 第二类的横纵坐标
y1 = torch.ones(100)                # class1 y data (tensor), shape=(100, 1) 第二类的标签全是1
x = torch.cat((x0, x1), 0).type(torch.FloatTensor)  # shape (200, 2) FloatTensor = 32-bit floating
y = torch.cat((y0, y1), ).type(torch.LongTensor)    # shape (200,) LongTensor = 64-bit integer
print(y.size())
# torch can only train on Variable, so convert them to Variable
x, y = Variable(x), Variable(y)

plt.scatter(x.data.numpy()[:, 0], x.data.numpy()[:, 1], c=y.data.numpy(), s=100, lw=0, cmap='RdYlGn')
plt.show()

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)   # hidden layer
        self.out = torch.nn.Linear(n_hidden, n_output)   # output layer

    def forward(self, x):
        x = F.relu(self.hidden(x))      # activation function for hidden layer
        x = self.out(x)
        return x
  
net = Net(n_feature=2, n_hidden=10, n_output=2)     # define the network
print(net)  # net architecture

# Loss and Optimizer
# Softmax is internally computed.
# Set parameters to be updated.
optimizer = torch.optim.SGD(net.parameters(), lr=0.02)
loss_func = torch.nn.CrossEntropyLoss()  # the target label is NOT an one-hotted

plt.ion()   # something about plotting
for t in range(100):
    out = net(x)                 # input x and predict based on x
    loss = loss_func(out, y)     # must be (1. nn output, 2. target), the target label is NOT one-hotted

    optimizer.zero_grad()   # clear gradients for next train
    loss.backward()         # backpropagation, compute gradients
    optimizer.step()        # apply gradients
    
    if t % 10 == 0 or t in [3, 6]:
        # plot and show learning process
        plt.cla()
        _, prediction = torch.max(F.softmax(out), 1)    # out (tuple, optional) – the result tuple of two output tensors (max, max_indices)
        pred_y = prediction.data.numpy().squeeze()
        target_y = y.data.numpy()
        plt.scatter(x.data.numpy()[:, 0], x.data.numpy()[:, 1], c=pred_y, s=100, lw=0, cmap='RdYlGn')
        accuracy = sum(pred_y == target_y)/200.
        plt.text(1.5, -4, 'Accuracy=%.2f' % accuracy, fontdict={'size': 20, 'color':  'red'})
        plt.show()
        plt.pause(0.1)

plt.ioff()

net2 = torch.nn.Sequential(
    torch.nn.Linear(1, 10),
    torch.nn.ReLU(),
    torch.nn.Linear(10, 1)
)

import torch
import torch.utils.data as Data
torch.manual_seed(1)    # reproducible
BATCH_SIZE = 5
x = torch.linspace(1, 10, 10)       # this is x data (torch tensor)
y = torch.linspace(10, 1, 10)       # this is y data (torch tensor)
torch_dataset = Data.TensorDataset(data_tensor=x, target_tensor=y)
loader = Data.DataLoader(
    dataset=torch_dataset,      # torch TensorDataset format 数据类型
    batch_size=BATCH_SIZE,      # mini batch size 训练一次的数据量
    shuffle=True,               # random shuffle for training 每次epoch的数据顺序是否被打乱
    num_workers=2,              # subprocesses for loading data 线程数
)
or epoch in range(3):   # train entire dataset 3 times 整个训练集用几次
    for step, (batch_x, batch_y) in enumerate(loader):  # for each training step
        # train your data...
        print('Epoch: ', epoch, '| Step: ', step, '| batch x: ',
              batch_x.numpy(), '| batch y: ', batch_y.numpy())