PyTorch——实现多层感知机（附完整代码）

参考链接

1. https://tangshusen.me/Dive-into-DL-PyTorch/#/chapter03_DL-basics/3.9_mlp-scratch
2. https://tangshusen.me/Dive-into-DL-PyTorch/#/chapter03_DL-basics/3.10_mlp-pytorch

加载数据

依然使用“Fashion-MNIST”数据集。

mnist_train = torchvision.datasets.FashionMNIST(root='~/Datasets/FashionMNIST', train=True, download=True, transform=transforms.ToTensor())
mnist_test = torchvision.datasets.FashionMNIST(root='~/Datasets/FashionMNIST', train=False, download=True, transform=transforms.ToTensor())

def get_fashion_mnist_labels(labels):
    text_labels = ['t-shirt', 'trouser', 'pullover', 'dress', 'coat',
                   'sandal', 'shirt', 'sneaker', 'bag', 'ankle boot']
    return [text_labels[int(i)] for i in labels]

def load_data_fashion_mnist(mnist_train, mnist_test, batch_size):
    if sys.platform.startswith('win'):
        num_workers = 0
    else:
        num_workers = 4
    train_iter = torch.utils.data.DataLoader(mnist_train, batch_size=batch_size, shuffle=True, num_workers=num_workers)
    test_iter = torch.utils.data.DataLoader(mnist_test, batch_size=batch_size, shuffle=False, num_workers=num_workers)
    return train_iter, test_iter

def show_fashion_mnist(images, labels):
    _, figs = plt.subplots(1, len(images), figsize=(12, 12))
    for f, img, lbl in zip(figs, images, labels):
        f.imshow(img.view((28, 28)).numpy())
        f.set_title(lbl)
        f.axes.get_xaxis().set_visible(False)
        f.axes.get_yaxis().set_visible(False)
    plt.show()

batch_size = 256
train_iter, test_iter = load_data_fashion_mnist(mnist_train, mnist_test, batch_size)

构建模型

使用两个矩阵相乘实现

num_inputs, num_outputs, num_hiddens = 784, 10, 256

W1 = torch.tensor(np.random.normal(0, 0.01, (num_inputs, num_hiddens)), dtype=torch.float, requires_grad=True)
b1 = torch.zeros(num_hiddens, dtype=torch.float, requires_grad=True)
W2 = torch.tensor(np.random.normal(0, 0.01, (num_hiddens, num_outputs)), dtype=torch.float, requires_grad=True)
b2 = torch.zeros(num_outputs, dtype=torch.float, requires_grad=True)

params = [W1, b1, W2, b2]

def relu(X):
    return torch.max(input=X, other=torch.tensor(0.0))

def net(X):
    X = X.view((-1, num_inputs))
    H = relu(torch.matmul(X, W1) + b1)
    return torch.matmul(H, W2) + b2

使用两个全连接层实现

num_inputs, num_outputs, num_hiddens = 784, 10, 256

class FlattenLayer(nn.Module):
    def __init__(self):
        super