数据封装、优化器及LOSS画图

数据封装mini-batch
参考：https://morvanzhou.github.io/tutorials/machine-learning/torch/3-05-train-on-batch/

import torch
import torch.utils.data as Data
torch.manual_seed(1)    # reproducible
BATCH_SIZE = 5      # 批训练的数据个数
x = torch.linspace(1, 10, 10)       # x data (torch tensor)
y = torch.linspace(10, 1, 10)       # y data (torch tensor)
# 先转换成 torch 能识别的 Dataset
torch_dataset = Data.TensorDataset(x, y)
# 把 dataset 放入 DataLoader
loader = Data.DataLoader(
    dataset=torch_dataset,      # torch TensorDataset format
    batch_size=BATCH_SIZE,      # mini batch size
    shuffle=True,               # 要不要打乱数据 (打乱比较好)
    num_workers=2,              # 多线程来读数据，win系统删去
)
for epoch in range(3):   # 训练所有!整套!数据 3 次
    for step, (batch_x, batch_y) in enumerate(loader):  # 每一步 loader 释放一小批数据用来学习
        # 假设这里就是你训练的地方...
        # 打出来一些数据
        print('Epoch: ', epoch, '| Step: ', step, '| batch x: ',
              batch_x.numpy(), '| batch y: ', batch_y.numpy())

优化器及LOSS画图代码
https://github.com/MorvanZhou/PyTorch-Tutorial/blob/master/tutorial-contents/306_optimizer.py#L2

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

# torch.manual_seed(1)    # reproducible

LR = 0.01
BATCH_SIZE = 32
EPOCH = 12

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

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

# put dateset into torch dataset
torch_dataset = Data.TensorDataset(x, y)
loader = Data.DataLoader(dataset=torch_dataset, batch_size=BATCH_SIZE, shuffle=True, )


# default network
class Net(torch.nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.hidden = torch.nn.Linear(1, 20)   # hidden layer
        self.predict = torch.nn.Linear(20, 1)   # 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

if __name__ == '__main__':
    # different nets
    net_SGD         = Net()
    net_Momentum    = Net()
    net_RMSprop     = Net()
    net_Adam        = Net()
    nets = [net_SGD, net_Momentum, net_RMSprop, net_Adam]

    # different optimizers
    opt_SGD         = torch.optim.SGD(net_SGD.parameters(), lr=LR)
    opt_Momentum    = torch.optim.SGD(net_Momentum.parameters(), lr=LR, momentum=0.8)
    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))
    optimizers = [opt_SGD, opt_Momentum, opt_RMSprop, opt_Adam]

    loss_func = torch.nn.MSELoss()
    losses_his = [[], [], [], []]   # record loss

    # training
    for epoch in range(EPOCH):
        print('Epoch: ', epoch)
        for step, (b_x, b_y) in enumerate(loader):          # for each training step
            for net, opt, l_his in zip(nets, optimizers, losses_his):
                output = net(b_x)              # get output for every net
                loss = loss_func(output, b_y)  # compute loss for every net
                opt.zero_grad()                # clear gradients for next train
                loss.backward()                # backpropagation, compute gradients
                opt.step()                     # apply gradients
                l_his.append(loss.data.numpy())     # loss recoder

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