PyTorch基本用法(九)——オプティマイザ

import torch
import matplotlib.pyplot as plt
import torch.nn.functional as F
import torch.utils.data as Data
from torch.autograd import Variable


#  
LR = 0.01
BATCH_SIZE = 32
EPOCH = 10


#  
x = torch.unsqueeze(torch.linspace(-1, 1, 1000), dim = 1)
y = x.pow(2) + 0.1  * torch.normal(torch.zeros(x.size()))

#  
plt.scatter(x.numpy(), y.numpy())
plt.show()

#  
dataset = Data.TensorDataset(data_tensor = x, target_tensor = y)

#  
loader = Data.DataLoader(dataset = dataset, batch_size = BATCH_SIZE, shuffle = True, num_workers = 2)

#  pytorch 
class Net(torch.nn.Module):
    
    def __init__(self, n_features, n_hidden, n_output):
        super(Net, self).__init__()
        self.hidden = torch.nn.Linear(n_features, n_hidden)
        self.predict = torch.nn.Linear(n_hidden, n_output)
    
    def forward(self, x):
        x = F.relu(self.hidden(x))
        y = self.predict(x)
        return y

#  
net_SGD = Net(1, 10, 1)
net_Momentum = Net(1, 10, 1)
net_RMSprop = Net(1, 10, 1)
net_Adam = Net(1, 10, 1)

#  
opt_SGD = torch.optim.SGD(net_SGD.parameters(), lr = LR)
opt_Momentum = torch.optim.SGD(net_Momentum.parameters(), lr = LR, momentum = 0.9)
opt_RMSprop = torch.optim.RMSprop(net_RMSprop.parameters(), lr = LR, alpha = 0.9)
opt_Adam = torch.optim.Adam(net_Adam.parameters(), lr = LR, betas= (0.9, 0.99))

nets = [net_SGD, net_Momentum, net_RMSprop, net_Adam]
optimizers = [opt_SGD, opt_Momentum, opt_RMSprop, opt_Adam]

#  
loss_func = torch.nn.MSELoss()

#  loss
loss_SGD = []
loss_Momentum = []
loss_RMSprop =[]
loss_Adam = []

#  loss
losses = [loss_SGD, loss_Momentum, loss_RMSprop, loss_Adam]

#  
for epoch in xrange(EPOCH):
    for step, (batch_x, batch_y) in enumerate(loader):
        var_x = Variable(batch_x)
        var_y = Variable(batch_y)
        for net, optimizer, loss_history in zip(nets, optimizers, losses):
            #  x 
            prediction = net(var_x)
            #  
            loss = loss_func(prediction, var_y)
            #  
            optimizer.zero_grad()
            #  
            loss.backward()
            #  
            optimizer.step()
            #  loss 
            loss_history.append(loss.data[0])

#  
labels = ['SGD', 'Momentum', 'RMSprop', 'Adam']
for i, loss_history in enumerate(losses):
    plt.plot(loss_history, label = labels[i])
plt.legend(loc = 'best')
plt.xlabel('Steps')
plt.ylabel('Loss')
plt.ylim((0, 0.2))
plt.show()

参考資料