【AI】Pytorch神经网络分类初探

Pytorch神经网络分类初探

1.数据准备

环境采用之前创建的Anaconda虚拟环境pytorch，为了方便查看每一步的返回值，可以使用Jupyter Notebook来进行开发。首先把需要的包导入进来

import torch
from torch import nn
from torch.utils.data import DataLoader
from torchvision import datasets
from torchvision.transforms import ToTensor

torch框架的数据输入依赖两个基类：torch.utils.data.DataLoader和torch.utils.data.Dataset，Dataset 存储样本及其相应的标签，DataLoader 将 Dataset 封装为迭代器。

为了方便使用数据，我们采用Mnist数据集

%matplotlib inline
from pathlib import Path
import requests

DATA_PATH = Path("data")
PATH = DATA_PATH / "mnist"

PATH.mkdir(parents=True, exist_ok=True)

URL = "http://deeplearning.net/data/mnist/"
FILENAME = "mnist.pkl.gz"

if not (PATH / FILENAME).exists():
        content = requests.get(URL + FILENAME).content
        (PATH / FILENAME).open("wb").write(content)

等待数据下载完毕，然后将数据读入进来。

import pickle
import gzip

with gzip.open((PATH / FILENAME).as_posix(), "rb") as f:
        ((x_train, y_train), (x_valid, y_valid), _) = pickle.load(f, encoding="latin-1")

读入进来的数据并不是tensor格式的，需要将其转化成Tensor格式

import torch

x_train, y_train, x_valid, y_valid = map(
    torch.tensor, (x_train, y_train, x_valid, y_valid)
)

最重要的一步，将其转换成dataset和dataloader

from torch.utils.data import TensorDataset
from torch.utils.data import DataLoader

train_ds = TensorDataset(x_train, y_train)
train_dl = DataLoader(train_ds, batch_size=bs, shuffle=True)

valid_ds = TensorDataset(x_valid, y_valid)
valid_dl = DataLoader(valid_ds, batch_size=bs * 2)

这样就完成了数据准备的工作

2.定义模型

这边直接引用官网教程的模型

# Get cpu, gpu or mps device for training.
device = (
    "cuda"
    if torch.cuda.is_available()
    else "mps"
    if torch.backends.mps.is_available()
    else "cpu"
)
print(f"Using {device} device")

# Define model
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

model = NeuralNetwork().to(device)
print(model)

将打印的结果放在下面，可以查看一下

Using cuda device
NeuralNetwork(
  (flatten): Flatten(start_dim=1, end_dim=-1)
  (linear_relu_stack): Sequential(
    (0): Linear(in_features=784, out_features=512, bias=True)
    (1): ReLU()
    (2): Linear(in_features=512, out_features=512, bias=True)
    (3): ReLU()
    (4): Linear(in_features=512, out_features=10, bias=True)
  )
)

3.定义模型损失函数和优化器

这里我们依旧使用官网教程中的直接来

loss_fn = nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr=1e-3)

这里的SGD是最基础的优化器，采用的是梯度递减的方式，其收敛的会比较慢，如果希望收敛快些，可以使用Adam方式。

4. 定义训练和测试函数

训练函数

def train(dataloader, model, loss_fn, optimizer):
    size = len(dataloader.dataset)
    model.train()
    for batch, (X, y) in enumerate(dataloader):
        X, y = X.to(device), y.to(device)

        # Compute prediction error
        pred = model(X)
        loss = loss_fn(pred, y)

        # Backpropagation
        loss.backward()
        optimizer.step()
        optimizer.zero_grad()

        if batch % 100 == 0:
            loss, current = loss.item(), (batch + 1) * len(X)
            print(f"loss: {loss:>7f}  [{current:>5d}/{size:>5d}]")

测试函数

def test(dataloader, model, loss_fn):
    size = len(dataloader.dataset)
    num_batches = len(dataloader)
    model.eval()
    test_loss, correct = 0, 0
    with torch.no_grad():
        for X, y in dataloader:
            X, y = X.to(device), y.to(device)
            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: \n Accuracy: {(100*correct):>0.1f}%, Avg loss: {test_loss:>8f} \n")

5.开始训练

epochs = 5
for t in range(epochs):
    print(f"Epoch {t+1}\n-------------------------------")
    train(train_dl, model, loss_fn, optimizer)
    test(valid_dl, model, loss_fn)
print("Done!")

6.模型保存

torch.save(model.state_dict(), "model.pth")
print("Saved PyTorch Model State to model.pth")

7.模型加载和使用模型预测

model = NeuralNetwork().to(device)
model.load_state_dict(torch.load("model.pth"))

模型预测

classes = [
    "0",
    "1",
    "2",
    "3",
    "4",
    "5",
    "6",
    "7",
    "8",
    "9",
]

model.eval()
x, y = train_ds[2][0], train_ds[2][1]
with torch.no_grad():
    x = x.to(device)
    pred = model(x)
    print(pred)
    predicted, actual = classes[pred.argmax(0)], classes[y]
    print(f'Predicted: "{predicted}", Actual: "{actual}"')

使用SGD优化器训练，训练5次的最高精度为76%，而使用Adam优化器第一个epoch的精度就已经达到了97%