import torch
from torch import nn
from d2l import torch as d2l
import matplotlib.pyplot as plt


batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)

# 实现一个具有但隐藏层的多层感知机，它包含256个隐藏单元
num_inputs, num_outputs, num_hiddens = 784, 10, 256

W1 = nn.Parameter(torch.randn(num_inputs, num_hiddens, requires_grad=True))
b1 = nn.Parameter(torch.zeros(num_hiddens, requires_grad=True))
W2 = nn.Parameter(torch.randn(num_hiddens, num_outputs, requires_grad=True))
b2 = nn.Parameter(torch.zeros(num_outputs, requires_grad=True))

params = [W1, b1, W2, b2]


# 实现ReLU激活函数
def relu(X):
    """
    ReLU函数
    :param X:一个tensor
    :return: 如果对应的X值小于0，返回0，反之返回X的值
    """
    a = torch.zeros_like(X)
    return torch.max(X, a)


# 实现模型
def net(X):
    X = X.reshape((-1, num_inputs))
    H = relu(X @ W1 + b1)
    return (H @ W2 + b2)


loss = nn.CrossEntropyLoss()

# 多层感知机训练
num_epochs, lr = 10, 0.1
updater = torch.optim.SGD(params, lr=lr)
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, updater)
plt.show()