pytorch 搭建神经网络的实现

目录

• 1 数据
  •  （1）导入数据
  • （2）数据集可视化
  • （3）为自己制作的数据集创建类
  • （4）数据集批处理
  • （5）数据预处理
• 2 神经网络
  • （1）定义神经网络类
  • （3）模型参数
• 3 最优化模型参数
  • （1）超参数
  • （2）损失函数
  • （3）优化方法
• 4 模型的训练与测试
  • （1）训练循环与测试循环
  • （2）禁用梯度跟踪
• 5 模型的保存、导入与GPU加速
  • （1）模型的保存与导入
  • （2）GPU加速
• 总结

import torch
from torchvision import datasets
from torchvision.transforms import ToTensor
import matplotlib.pyplot as plt
import os
os.environ["KMP_DUPLICATE_LIB_OK"] = "TRUE"	# 没有这句会报错，具体原因我也不知道

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

test_data = datasets.FashionMNIST(
    root="../data",
    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",
}
figure = plt.figure(figsize=(8, 8))
cols, rows = 3, 3
for i in range(1, cols * rows + 1):
    # 从0-len(training_data)中随机生成一个数字（不包括右边界）
    sample_idx = torch.randint(len(training_data), size=(1,)).item() 
    img, label = training_data[sample_idx] # 获得图片和标签
    figure.add_subplot(rows, cols, i)
    plt.title(labels_map[label])
    plt.axis("off")                        # 坐标轴不可见
    plt.imshow(img.squeeze(), cmap="gray") # 显示灰度图
plt.show()

import os
import pandas as pd
from torch.utils.data import Dataset
from torchvision.io import read_image

class CustomImageDataset(Dataset):
    def __init__(self, annotations_file, img_dir, transform=None, target_transform=None):
        self.img_labels = pd.read_csv(annotations_file)
        self.img_dir = img_dir
        self.transform = transform
        self.target_transform = target_transform

    def __len__(self):
        return len(self.img_labels)

    def __getitem__(self, idx):
        img_path = os.path.join(self.img_dir, self.img_labels.iloc[idx, 0])
        image = read_image(img_path)
        label = self.img_labels.iloc[idx, 1]
        if self.transform:
            image = self.transform(image)
        if self.target_transform:
            label = self.target_transform(label)
        return image, label

from torch.utils.data import DataLoader

train_dataloader = DataLoader(training_data, batch_size=64, shuffle=True) 
# train_dataloader是一个DataLoader类的对象
test_dataloader = DataLoader(test_data, batch_size=64, shuffle=True)

for batch_index, (features, label) in enumerate(train_dataloader):
    print(batch_index)
    print(f"Feature batch shape: {features.size()}")
    print(f"Labels batch shape: {label.size()}")
    img = features[0].squeeze()
    label = label[0]
    plt.imshow(img, cmap="gray")
    plt.show()
    print(f"Label: {label}")
    break

for batch_index, (features, label) in enumerate(train_dataloader):
    print(batch_index)
    print(f"Feature batch shape: {features.size()}")
    print(f"Labels batch shape: {label.size()}")
    img = features[0].squeeze()
    label = label[0]
    plt.imshow(img, cmap="gray")
    plt.show()
    print(f"Label: {label}")
    break

import torch
from torchvision import datasets
from torchvision.transforms import ToTensor, Lambda

ds = datasets.FashionMNIST(
    root="data",
    train=True,
    download=True,
    transform=ToTensor(),
    target_transform=Lambda(lambda y: torch.zeros(10, dtype=torch.float).scatter_(dim=0, index=torch.tensor(y), value=1))
)

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

    def forward(self, x):
        x = self.flatten(x)					# 打平层
        logits = self.linear_relu_stack(x)	# 线性激活层
        return logits

model = NeuralNetwork()
print(model)

X = torch.rand(1, 28, 28)	# 生成一个样本
logits = model(X)							# 将样本输入到模型中，自动调用forward方法
print(logits.size())						
pred_probab = nn.Softmax(dim=1)(logits)		# 实例化一个Softmax对象，并通过对象调用
y_pred = pred_probab.argmax(1)				# 获得概率最大索引
print(f"Predicted class: {y_pred}")

input_image = torch.rand(3,28,28)
print(input_image.size())

layer1 = nn.Linear(in_features=28*28, out_features=20)
hidden1 = layer1(flat_image)
print(hidden1.size())

w = torch.rand(784, 20)
b = torch.rand((1, 20))
hidden2 = flat_image @ w + b
print(hidden2.size())

seq_modules = nn.Sequential(
    flatten,		# 在nn.Sequential中可以调用其他模块
    layer1,
    nn.ReLU(),
    nn.Linear(20, 10)
)
input_image = torch.rand(3,28,28)
logits = seq_modules(input_image)

para_list = list(model.parameters())

# 将参数生成器转换成列表之后，列表的第一个元素是w，第二个元素是b
print(type(para_list[0]))
print(f"number of linear_layers :{len(para_list)/2}")
print("weights:")
print(para_list[0][:2])  # 只切出两个样本来显示
print("bias:")
print(para_list[1][:2]) 
print("
the shape of first linear layer:", para_list[0].shape)

print("Model structure: ", model, "

")

for name, param in model.named_parameters():
    print(f"Layer: {name} | Size: {param.size()} | Values : 
{param[:2]} 
")
    # 只切出前两行显示

learning_rate = 1e-3
batch_size = 64
epochs = 5

# Initialize the loss function
loss_fn = nn.CrossEntropyLoss()

optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)

def train_loop(dataloader, model, loss_fn, optimizer):
    size = len(dataloader.dataset)
    for batch, (X, y) in enumerate(dataloader):
        # Compute prediction and loss，下面两步相当于绘制计算图
        pred = model(X)
        loss = loss_fn(pred, y)

        # Backpropagation
        optimizer.zero_grad()	# 梯度信息清零
        loss.backward()			# 反向传播
        optimizer.step()		# 一旦有了梯度，就可以更新参数

        if batch % 100 == 0:
            loss, current = loss.item(), batch * len(X)
            print(f"loss: {loss:>7f}  [{current:>5d}/{size:>5d}]")


def test_loop(dataloader, model, loss_fn):
    size = len(dataloader.dataset)
    num_batches = len(dataloader)
    test_loss, correct = 0, 0

    with torch.no_grad():		# 禁用梯度跟踪，后面会讲
        for X, y in dataloader:
            pred = model(X)
            test_loss += loss_fn(pred, y).item()
            correct += (pred.argmax(1) == y).type(torch.float).sum().item()

    test_loss /= num_batches
    correct /= size
    print(f"Test Error: 
 Accuracy: {(100*correct):>0.1f}%, Avg loss: {test_loss:>8f} 
")

for t in range(epochs):
    print(f"Epoch {t+1}
-------------------------------")
    train_loop(train_dataloader, model, loss_fn, optimizer)
    test_loop(test_dataloader, model, loss_fn)
print("Done!")

test_features, test_labels = next(iter(test_dataloader))
logits = model(test_features[0])
pred_probab = nn.Softmax(dim=1)(logits)
pred = pred_probab.argmax(1)

img = test_features[0].squeeze()    # 将长度为1的维度去掉
true_label = test_labels[0]
plt.imshow(img, cmap="gray")
plt.show()
print(f"True label: {true_label}")
print(f"Predict: {pred.item()}")

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

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

# 保存模型参数
torch.save(model.state_dict(), "./model_weights.pth")
# 保存模型结构
torch.save(model, "./model.pth")

# 导入模型结构
model_loaded = torch.load("./model.pth") 
# 如果原来的model在cuda:0上，那么导入之后，model_loaded也在cuda:0上

# 导入模型参数
model_loaded.load_state_dict(torch.load("model_weights.pth"))

# 实例化一个NeuralNetwork对象
model_loaded = NeuralNetwork() # model_loaded默认是CPU中
# 导入模型参数
model_loaded.load_state_dict(torch.load("./gdrive/MyDrive/model_weights.pth"))

test_features, test_labels = next(iter(test_dataloader))
logits = model_loaded(test_features[0])   # 使用导入的模型
pred_probab = nn.Softmax(dim=1)(logits)
pred = pred_probab.argmax(1)

img = test_features[0].squeeze()    # 将长度为1的维度去掉
true_label = test_labels[0]
plt.imshow(img, cmap="gray")
plt.show()
print(f"True label: {true_label}")
print(f"Predict: {pred.item()}")

# We can move our tensor to the GPU if available
device = "cuda" if torch.cuda.is_available() else "cpu"
print("Using {} device".format(device))

model = NeuralNetwork().to(device)

X = torch.rand(1, 28, 28, device=device)	# 创建时指定设备
Y = torch.rand(10).to(device)				# 创建后转移

device = torch.device(‘cuda:2")
# 2是设备号，假如有八张显卡，那么编号就是0―7

# coding=utf-8
import torch
import torch.nn as nn
from torchvision import datasets
from torch.utils.data import DataLoader
from torchvision.transforms import ToTensor
import matplotlib.pyplot as plt
import os
os.environ["KMP_DUPLICATE_LIB_OK"] = "TRUE"	# 没有这句会报错，具体原因我也不知道

# 导入数据
training_data = datasets.FashionMNIST(
    root="../data",
    train=True,
    download=True,
    transform=ToTensor()
)
test_data = datasets.FashionMNIST(
    root="../data",
    train=False,
    download=True,
    transform=ToTensor()
)

# 定义超参数
# 之所以在这个地方定义，是因为在初始化DataLoader时需要用到batch_size
learning_rate = 1e-3
batch_size = 64
epochs = 5
train_dataloader = DataLoader(training_data, batch_size=batch_size, shuffle=True)
# train_dataloader是一个DataLoader类的对象
test_dataloader = DataLoader(test_data, batch_size=batch_size, shuffle=True)


# 搭建神经网络
class NeuralNetwork(nn.Module):
    def __init__(self):
        super(NeuralNetwork, self).__init__()
        self.flatten = nn.Flatten()				# 打平
        self.linear_relu_stack = nn.Sequential(
            nn.Linear(28*28, 512),		# 线性层
            nn.ReLU(),					# 激活层
            nn.Linear(512, 512),
            nn.ReLU(),
            nn.Linear(512, 10),
            nn.ReLU()
        )

    def forward(self, x):
        x = self.flatten(x)					# 打平层
        logits = self.linear_relu_stack(x)	# 线性激活层
        return logits

# 确定使用设备
device = "cuda" if torch.cuda.is_available() else "cpu"

# 实例化一个神经网络类
model = NeuralNetwork().to(device)

# 确定损失函数
loss_fn = nn.CrossEntropyLoss()

# 确定优化器
optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)


# 封装训练过程
def train_loop(dataloader, model, loss_fn, optimizer):
    size = len(dataloader.dataset)
    for batch, (X, y) in enumerate(dataloader):
        X, y = X.to(device), y.to(device) # 将样本和标签转移到device中
        # Compute prediction and loss，下面两步相当于绘制计算图
        pred = model(X)
        loss = loss_fn(pred, y)

        # Backpropagation
        optimizer.zero_grad()	# 梯度信息清零
        loss.backward()			# 反向传播
        optimizer.step()		# 一旦有了梯度，就可以更新参数

        if batch % 100 == 0:
            loss, current = loss.item(), batch * len(X)
            print(f"loss: {loss:>7f}  [{current:>5d}/{size:>5d}]")
            

# 封装测试过程
def test_loop(dataloader, model, loss_fn):
    size = len(dataloader.dataset)
    num_batches = len(dataloader)
    test_loss, correct = 0, 0

    with torch.no_grad():
        for X, y in dataloader:
            X, y = X.to(device), y.to(device)  # 将样本和标签转移到device中
            pred = model(X)
            test_loss += loss_fn(pred, y).item()
            correct += (pred.argmax(1) == y).type(torch.float).sum().item()

    test_loss /= num_batches
    correct /= size
    print(f"Test Error: 
 Accuracy: {(100*correct):>0.1f}%, Avg loss: {test_loss:>8f} 
")

# 训练
for t in range(epochs):
    print(f"Epoch {t+1}
-------------------------------")
    train_loop(train_dataloader, model, loss_fn, optimizer)
    test_loop(test_dataloader, model, loss_fn)
print("Done!")

# 保存模型参数
torch.save(model.state_dict(), "./model_weights.pth")
# 保存模型结构
torch.save(model, "./model.pth")

# 导入模型结构
model_loaded = torch.load("./model.pth")    # 模型自动导入到GPU当中
# 导入模型参数
model_loaded.load_state_dict(torch.load("model_weights.pth"))

# 用导入的模型测试
test_features, test_labels = next(iter(test_dataloader))
test_features = test_features.to(device)
logits = model_loaded(test_features[0])   # 使用导入的模型
pred_probab = nn.Softmax(dim=1)(logits)
pred = pred_probab.argmax(1)

# 可视化
img = test_features[0].squeeze()    # 将长度为1的维度去掉
img = img.to("cpu")              # 绘图时，需要将张量转回到CPU当中
true_label = test_labels[0]   # 标签是否转移到CPU无所谓，因为没有用于plt的方法中
plt.imshow(img, cmap="gray")
plt.show()
print(f"True label: {true_label}")
print(f"Predict: {pred.item()}")