数据可视化

import torch
from torch.utils.data import Dataset
from torchvision import datasets
from torchvision.transforms import ToTensor
import matplotlib.pyplot as plt


training_data = datasets.FashionMNIST(
    root="data1",
    train=True,
    download=True,
    transform=ToTensor()
)

test_data = datasets.FashionMNIST(
    root="data1",
    train=False,
    download=True,
    transform=ToTensor()
)

labels_map = {
    0: "T-Shirt",
    1: "Trouser",
    2: "Pullover",
    3: "Dress",
    4: "Coat",
    5: "Sandal",
    6: "Shirt",
    7: "Sneaker",
    8: "Bag",
    9: "Ankle Boot",
}
cols, rows = 3, 3
for i in range(1, cols * rows + 1):
    sample_idx = torch.randint(len(training_data), size=(1,)).item() #用于随机取出一个training_data
    img, label = training_data[sample_idx]
    plt.subplot(3,3,i) #此处i必须是1开始
    plt.title(labels_map[label])
    plt.axis("off")
    plt.imshow(img.squeeze(), cmap="gray")
plt.show()

在这里插入图片描述

切换设备device

device = (
    "cuda"
    if torch.cuda.is_available()
    else "mps"
    if torch.backends.mps.is_available()
    else "cpu"
)
print(f"Using {device} device")

定义类

class NeuralNetwork(nn.Module):
    def __init__(self):
        super().__init__()
        self.flatten = nn.Flatten()
        self.linear_relu_stack = nn.Sequential(
            nn.Linear(28*28, 512),
            nn.ReLU(),
            nn.Linear(512, 512),
            nn.ReLU(),
            nn.Linear(512, 10),
        )

    def forward(self, x):
        x = self.flatten(x)
        logits = self.linear_relu_stack(x)
        return logits

打印每层的参数大小

print(f"Model structure: {model}\n\n")

for name, param in model.named_parameters():
    print(f"Layer: {name} | Size: {param.size()} | Values : {param[:2]} \n")

自动微分

详见文章Variable
需要优化的参数需要加requires_grad=True，会计算这些参数对于loss的梯度

import torch

x = torch.ones(5)  # input tensor
y = torch.zeros(3)  # expected output
w = torch.randn(5, 3, requires_grad=True)
b = torch.randn(3, requires_grad=True)
z = torch.matmul(x, w)+b
loss = torch.nn.functional.binary_cross_entropy_with_logits(z, y)

计算梯度

计算导数

loss.backward()
print(w.grad)
print(b.grad)

禁用梯度追踪

训练好后进行测试，也就是不要更新参数时使用

z = torch.matmul(x, w)+b
print(z.requires_grad)

with torch.no_grad():
    z = torch.matmul(x, w)+b
print(z.requires_grad)

优化模型参数

调用optimizer.zero_grad()来重置模型参数的梯度。梯度会默认累加，为了防止重复计算（梯度），我们在每次遍历中显式的清空（梯度累加值）。
调用loss.backward()来反向传播预测误差。PyTorch对每个参数分别存储损失梯度。
我们获取到梯度后，调用optimizer.step()来根据反向传播中收集的梯度来调整参数。

optmizer.zero_grad()
loss.backward()
optmizer.step()

模型保存

import torch
import torchvision.models as models

model = models.vgg16(weights='IMAGENET1K_V1')
torch.save(model.state_dict(), 'model_weights.pth')

模型加载

model = models.vgg16() # we do not specify ``weights``, i.e. create untrained model
model.load_state_dict(torch.load('model_weights.pth'))
model.eval()